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

    Neuronpedia

    INDEX
    Explanations

    identity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зрост
    -0.06
    _lin
    -0.06
    sidebar
    -0.06
     چون
    -0.06
    /////////////////////////////////////////////////////////////////////////////↵
    -0.06
    _deploy
    -0.06
    拓
    -0.06
    “But
    -0.06
     Ağ
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
     identity
    0.09
     사망
    0.08
     identifies
    0.07
     Chapman
    0.07
     Cream
    0.07
     Heidi
    0.07
     identities
    0.07
     tempfile
    0.07
     Detail
    0.07
     SECRET
    0.07
    Act Density 0.012%

    No Known Activations