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

    Neuronpedia

    INDEX
    Explanations

    _ASSUME

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    297
    -0.07
     Phot
    -0.07
     лист
    -0.07
    396
    -0.07
    342
    -0.07
    ieval
    -0.07
    фт
    -0.07
     karak
    -0.06
     مهندسی
    -0.06
    ------+
    -0.06
    POSITIVE LOGITS
    _ASSUME
    0.13
    busy
    0.08
     Despite
    0.07
     promise
    0.07
     prompting
    0.06
    assume
    0.06
    Barrier
    0.06
     assessing
    0.06
    -figure
    0.06
     Rush
    0.06
    Act Density 0.000%

    No Known Activations