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

    Neuronpedia

    INDEX
    Explanations

    legal complaints/investigations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ############################################################################
    -0.07
    _faces
    -0.07
    ObjectName
    -0.06
    (opt
    -0.06
     único
    -0.06
    _bias
    -0.06
     Fraud
    -0.06
    clave
    -0.06
    (hdr
    -0.06
    传奇
    -0.06
    POSITIVE LOGITS
    рії
    0.07
     persever
    0.06
     SEA
    0.06
     yakın
    0.06
    reet
    0.06
     chuckled
    0.06
     mad
    0.06
     uit
    0.06
     curious
    0.06
    換
    0.06
    Act Density 0.022%

    No Known Activations