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

    Neuronpedia

    INDEX
    Explanations

    hypothetical/conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     공식
    -0.07
    e
    -0.07
     authoritative
    -0.07
    /~
    -0.07
    ına
    -0.06
    Введите
    -0.06
     paginate
    -0.06
    agu
    -0.06
    closing
    -0.06
    science
    -0.06
    POSITIVE LOGITS
     Kauf
    0.07
    627
    0.06
     woods
    0.06
     Beginning
    0.06
     ›
    0.06
    leanor
    0.06
     cresc
    0.06
     asks
    0.06
     importantly
    0.06
    _bus
    0.06
    Act Density 0.004%

    No Known Activations