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

    Neuronpedia

    INDEX
    Explanations

    of the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Metropolitan
    -0.07
    .Never
    -0.06
     jobject
    -0.06
     Aleks
    -0.06
     Barr
    -0.06
     cof
    -0.06
    ्तर
    -0.06
    ácil
    -0.06
     devlet
    -0.06
    _blocking
    -0.06
    POSITIVE LOGITS
    _ALIAS
    0.06
     slips
    0.06
     Public
    0.06
     =================================================================
    0.06
    \Storage
    0.06
     ⓘ
    0.06
    awaii
    0.06
     interfaces
    0.06
     CONF
    0.06
     OH
    0.06
    Act Density 0.090%

    No Known Activations