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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pride
    -0.07
     pelvic
    -0.07
     Wheat
    -0.07
     Π
    -0.07
     budouc
    -0.07
     G
    -0.06
    .mask
    -0.06
    <int
    -0.06
     SIL
    -0.06
     QUE
    -0.06
    POSITIVE LOGITS
    γγελ
    0.07
    bugs
    0.07
     banka
    0.06
    atto
    0.06
    addListener
    0.06
     �
    0.06
     "+↵
    0.06
    acemark
    0.06
    tempt
    0.06
    нт
    0.06
    Act Density 0.007%

    No Known Activations