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

    Neuronpedia

    INDEX
    Explanations

    Court testimony

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    атег
    -0.07
     inversion
    -0.07
     Strateg
    -0.07
    Deserialize
    -0.07
     gazet
    -0.07
     Tradable
    -0.07
    kola
    -0.07
    (t
    -0.06
     Permanent
    -0.06
    ولوژی
    -0.06
    POSITIVE LOGITS
    _disc
    0.06
    kf
    0.06
    のだ
    0.06
    .dashboard
    0.06
    _SUS
    0.06
     př
    0.06
     Cout
    0.06
     apparent
    0.06
    	person
    0.06
    庫
    0.06
    Act Density 0.011%

    No Known Activations