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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scanner
    -0.07
    (Void
    -0.07
    --[[
    -0.07
     mai
    -0.07
     bt
    -0.06
     dictate
    -0.06
    /fonts
    -0.06
     Antique
    -0.06
    793
    -0.06
     badly
    -0.06
    POSITIVE LOGITS
    -establish
    0.07
    約
    0.07
    imi
    0.07
     законодавства
    0.06
     امنیت
    0.06
     spacer
    0.06
    ssi
    0.06
     occupation
    0.06
     düşür
    0.06
     homogeneous
    0.06
    Act Density 0.050%

    No Known Activations