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

    Neuronpedia

    INDEX
    Explanations

    Code and technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icky
    -0.07
    ientes
    -0.07
    úc
    -0.07
    ʇ
    -0.06
    -↵↵
    -0.06
    䓖
    -0.06
     New
    -0.06
     FlatButton
    -0.06
    ương
    -0.06
    שנתי
    -0.06
    POSITIVE LOGITS
    Retrieve
    0.08
    HH
    0.07
     Policies
    0.07
     Gef
    0.07
    /k
    0.07
     Arist
    0.07
     Breath
    0.06
    AZ
    0.06
    .Repository
    0.06
    孩子的
    0.06
    Act Density 0.000%

    No Known Activations