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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and notation

    oai_token-act-pair · gemini-2.0-flash

    quad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }_{\
    -0.83
    <sub>
    -0.70
     }_{
    -0.67
    }}_{\
    -0.66
    sizeCache
    -0.63
     $_{\
    -0.63
     _{\
    -0.60
    $_
    -0.60
    }_{\
    -0.60
     $_{
    -0.59
    POSITIVE LOGITS
    Привет
    0.53
     defaultstate
    0.50
    RunAsync
    0.48
    فحة
    0.48
    matic
    0.48
    rcl
    0.47
    ToTop
    0.47
     trick
    0.47
    スーパー
    0.47
    hower
    0.47
    Act Density 4.519%

    No Known Activations