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

    Neuronpedia

    INDEX
    Explanations

    =""/>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marilyn
    -0.07
    ")));↵↵
    -0.07
    자의
    -0.06
     userType
    -0.06
     Georgetown
    -0.06
    续
    -0.06
     needless
    -0.06
    '";↵
    -0.06
    Initialize
    -0.06
    ."'";↵
    -0.06
    POSITIVE LOGITS
    :"",
    0.06
     aberr
    0.06
     Worship
    0.06
     ум
    0.06
    ธน
    0.06
     Pick
    0.06
     affirm
    0.06
    啊
    0.06
    .getToken
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations