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

    Neuronpedia

    INDEX
    Explanations

    early intervention, prevention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erg
    -0.06
    ocyte
    -0.06
     pequ
    -0.06
    _eval
    -0.06
     Superman
    -0.06
     pand
    -0.06
    iêu
    -0.06
    _pag
    -0.06
     Kč
    -0.06
    /win
    -0.06
    POSITIVE LOGITS
     capitalize
    0.06
     Front
    0.06
     Rules
    0.06
     combines
    0.06
     Spotlight
    0.06
     cupcakes
    0.06
     Rule
    0.06
     zad
    0.06
     pump
    0.06
    _HOT
    0.06
    Act Density 0.048%

    No Known Activations