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

    Neuronpedia

    INDEX
    Explanations

    software/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Locale
    -0.07
    	btn
    -0.07
    Annual
    -0.07
    lias
    -0.07
     windy
    -0.07
     lg
    -0.07
     coin
    -0.07
    bac
    -0.07
     annual
    -0.07
     immoral
    -0.07
    POSITIVE LOGITS
    _password
    0.07
    ":
    0.07
    _GUID
    0.07
    pieczeńst
    0.07
     succesfully
    0.07
     Authorities
    0.06
    _converter
    0.06
     mell
    0.06
     SEND
    0.06
     plata
    0.06
    Act Density 0.000%

    No Known Activations