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

    Neuronpedia

    INDEX
    Explanations

    Police observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lüğü
    -0.07
    服
    -0.07
    iversal
    -0.07
    _while
    -0.06
     crawler
    -0.06
    绩
    -0.06
     над
    -0.06
    ยา
    -0.06
    anc
    -0.06
     đọ
    -0.06
    POSITIVE LOGITS
    -adjust
    0.07
    onden
    0.07
    PEG
    0.07
    Sink
    0.06
     شیر
    0.06
    .Second
    0.06
    solid
    0.06
    xae
    0.06
    cele
    0.06
    ('</
    0.06
    Act Density 0.015%

    No Known Activations