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

    Neuronpedia

    INDEX
    Explanations

    expressions or phrases that indicate specific phenomena or concepts

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

    identifying by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.63
    évaluateur
    -0.55
    __':
    -0.52
    PINES
    -0.52
     Roskov
    -0.50
    tagHelperRunner
    -0.49
     beginnetje
    -0.49
    +:+
    -0.48
    complexContent
    -0.47
     estekak
    -0.45
    POSITIVE LOGITS
     called
    0.67
    called
    0.59
     CALLED
    0.54
     chamado
    0.52
     Called
    0.52
     nazy
    0.51
     llamada
    0.50
     chamada
    0.48
     llamado
    0.48
     genoemd
    0.47
    Act Density 0.176%

    No Known Activations