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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olved
    -0.07
     weighs
    -0.06
    .numpy
    -0.06
    发明
    -0.06
    躺在床上
    -0.06
     advanced
    -0.06
    敏感
    -0.06
    分开
    -0.06
     게
    -0.06
    _security
    -0.06
    POSITIVE LOGITS
    CriticalSection
    0.07
    clinic
    0.07
    UNCT
    0.07
    ligne
    0.07
    �
    0.07
    .IsNull
    0.07
    crest
    0.06
     ulaş
    0.06
    (cuda
    0.06
    VS
    0.06
    Act Density 0.119%

    No Known Activations