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

    Neuronpedia

    INDEX
    Explanations

    Citations and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шел
    -0.07
    _CONSTANT
    -0.07
    soles
    -0.06
    .verify
    -0.06
     Replacement
    -0.06
     Ваш
    -0.06
     VER
    -0.06
    хран
    -0.06
     rave
    -0.06
    ीम
    -0.06
    POSITIVE LOGITS
    .nome
    0.06
     selbst
    0.06
     навч
    0.06
     cookie
    0.06
     architectural
    0.06
    BagConstraints
    0.06
     OnTrigger
    0.06
    PLICATE
    0.06
    styleType
    0.06
    臺
    0.06
    Act Density 0.002%

    No Known Activations