Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms and phrases associated with definitions and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    and phrases being defined or used

    np_acts-logits-general · gemini-2.0-flash

    terms used interchangeably

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Called
    -0.55
     detto
    -0.55
     llamadas
    -0.54
     llamada
    -0.53
     llamado
    -0.52
     gena
    -0.52
     prévoit
    -0.51
    makeConstraints
    -0.50
     chamado
    -0.50
     équipé
    -0.49
    POSITIVE LOGITS
     used
    0.81
     referring
    0.74
     connotation
    0.72
     connotations
    0.71
     interchangeably
    0.71
     coined
    0.70
    used
    0.70
     synonymous
    0.69
    WriteAttribute
    0.67
     usage
    0.67
    Act Density 0.355%

    No Known Activations