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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     libraries
    -0.07
     Lies
    -0.07
     الرم
    -0.06
     Suites
    -0.06
     Fam
    -0.06
    .Prot
    -0.06
     للد
    -0.06
    _modal
    -0.06
     hasta
    -0.06
     새로운
    -0.06
    POSITIVE LOGITS
    vla
    0.08
     Ging
    0.07
    _ra
    0.07
    \
    0.06
    =e
    0.06
     soo
    0.06
    ohana
    0.06
     Whe
    0.06
    TouchUpInside
    0.06
    _qs
    0.06
    Act Density 0.004%

    No Known Activations