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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ör
    -0.07
    /am
    -0.07
    graph
    -0.07
    stringValue
    -0.07
     vem
    -0.07
    必
    -0.07
     unlocking
    -0.06
    -E
    -0.06
    vote
    -0.06
    encode
    -0.06
    POSITIVE LOGITS
     Traits
    0.07
     challeng
    0.07
     entfer
    0.07
    ię
    0.07
     источ
    0.07
    那儿
    0.07
    EmailAddress
    0.07
     mainAxisAlignment
    0.07
    טין
    0.07
     dimin
    0.06
    Act Density 0.001%

    No Known Activations