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

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ontrol
    -0.07
     досвід
    -0.06
    _related
    -0.06
    -ra
    -0.06
     rhetorical
    -0.06
    ına
    -0.06
    _notifications
    -0.06
    wi
    -0.06
    finalize
    -0.06
     Nero
    -0.06
    POSITIVE LOGITS
     زمان
    0.07
     Sparks
    0.07
     TForm
    0.07
    .BatchNorm
    0.06
     hydro
    0.06
     크
    0.06
    (db
    0.06
     InkWell
    0.06
    asad
    0.06
    .parseDouble
    0.06
    Act Density 0.013%

    No Known Activations