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

    Neuronpedia

    INDEX
    Explanations

    ives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lik
    -0.07
    액
    -0.07
    .correct
    -0.06
    �
    -0.06
    ฐาน
    -0.06
    黎
    -0.06
     philanth
    -0.06
     सदस
    -0.06
     Крім
    -0.06
    .favorite
    -0.06
    POSITIVE LOGITS
     bob
    0.07
     '../
    0.06
     öncelik
    0.06
    223
    0.06
    373
    0.06
     feminine
    0.06
     diminished
    0.06
    421
    0.06
    Hall
    0.06
    cip
    0.06
    Act Density 0.000%

    No Known Activations