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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     degrading
    -0.09
     varen
    -0.08
     junio
    -0.08
     interp
    -0.08
     ness
    -0.08
     mars
    -0.08
     filler
    -0.08
    antis
    -0.08
    ాయని
    -0.07
     degrad
    -0.07
    POSITIVE LOGITS
     outbreak
    0.09
     Algorithm
    0.08
    lect
    0.08
     hon
    0.08
     വ്യക്തമ
    0.08
     Hague
    0.08
    _algorithm
    0.08
     emerald
    0.08
    abo
    0.08
     suites
    0.08
    Act Density 0.636%

    No Known Activations