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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms associated with input/output operations and data handling

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

    programming verbs like encode, parse, read

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.78
     poffible
    -0.67
    endphp
    -0.66
     fhort
    -0.66
     للمعارف
    -0.66
    rungsseite
    -0.65
     
    -0.65
    lankton
    -0.64
     ſtand
    -0.61
    IntoConstraints
    -0.61
    POSITIVE LOGITS
    canActivate
    0.45
     mergeFrom
    0.35
    invokeLater
    0.33
    RTSC
    0.32
     Using
    0.31
     ouverte
    0.31
     using
    0.30
    ReusableCell
    0.30
    destroyAll
    0.30
     kirjo
    0.29
    Act Density 0.024%

    No Known Activations