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

    Neuronpedia

    INDEX
    Explanations

    ");

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inform
    -0.06
     zak
    -0.06
    _LOCATION
    -0.06
    战争
    -0.06
    ابه
    -0.06
    ,...↵
    -0.06
     Randall
    -0.06
    чества
    -0.06
     처
    -0.05
     spirituality
    -0.05
    POSITIVE LOGITS
     minHeight
    0.07
    .cp
    0.07
     rooted
    0.07
    '^$',
    0.07
     verificar
    0.06
    ível
    0.06
     shielding
    0.06
     bols
    0.06
    /email
    0.06
    _reload
    0.06
    Act Density 0.000%

    No Known Activations