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

    Neuronpedia

    INDEX
    Explanations

    Listicle introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ileen
    -0.08
    236
    -0.07
    μαν
    -0.06
     ryb
    -0.06
     Kami
    -0.06
     Processing
    -0.06
    iesz
    -0.06
     अग
    -0.06
     adres
    -0.06
     влад
    -0.06
    POSITIVE LOGITS
    uates
    0.07
    -edit
    0.07
     jacket
    0.07
    _verification
    0.06
     addiction
    0.06
    IntArray
    0.06
     laten
    0.06
     aest
    0.06
    (min
    0.06
    .componentInstance
    0.06
    Act Density 0.096%

    No Known Activations