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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᐃ
    -0.07
    處
    -0.07
    ж
    -0.07
    ｲ
    -0.06
    .flow
    -0.06
    Nm
    -0.06
    ден
    -0.06
    hé
    -0.06
     hình
    -0.06
     infectious
    -0.06
    POSITIVE LOGITS
    .XtraGrid
    0.07
    modern
    0.07
     Marg
    0.07
     Concern
    0.07
    优雅
    0.07
     männ
    0.06
     discrim
    0.06
     литер
    0.06
     Skinny
    0.06
     polít
    0.06
    Act Density 0.024%

    No Known Activations