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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生成
    -0.06
    .Int
    -0.06
     Probe
    -0.06
    ありません
    -0.06
    SPAN
    -0.06
    Suppress
    -0.06
    �
    -0.06
    Dlg
    -0.06
    さんの
    -0.06
    -time
    -0.06
    POSITIVE LOGITS
    (fh
    0.07
     enough
    0.06
     reinforces
    0.06
    ClearColor
    0.06
     Mourinho
    0.06
     zdravot
    0.06
    _authentication
    0.06
    letcher
    0.06
    wel
    0.06
    猫
    0.06
    Act Density 0.001%

    No Known Activations