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

    Neuronpedia

    INDEX
    Explanations

    cats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mill
    -0.07
    gress
    -0.07
     magnet
    -0.07
     succ
    -0.07
     Wig
    -0.07
     dirección
    -0.06
    кування
    -0.06
     Claims
    -0.06
     helpers
    -0.06
     Return
    -0.06
    POSITIVE LOGITS
     воспал
    0.06
    Angular
    0.06
    disposed
    0.06
    (','
    0.06
     overturn
    0.06
     Certif
    0.06
    challenge
    0.06
    _CHARSET
    0.06
     Missing
    0.06
     lassen
    0.06
    Act Density 0.405%

    No Known Activations