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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']],
    -0.07
    �
    -0.06
    _equiv
    -0.06
    613
    -0.06
     versch
    -0.06
    612
    -0.06
    (gui
    -0.06
     baru
    -0.06
     cheg
    -0.06
     implemented
    -0.06
    POSITIVE LOGITS
    Lab
    0.06
     downward
    0.06
     Dear
    0.06
     Qualified
    0.06
     И
    0.06
    惊
    0.06
    RD
    0.06
    _NAMESPACE
    0.06
     qualify
    0.06
    شمالی
    0.06
    Act Density 0.004%

    No Known Activations