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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiener
    -0.07
    _seek
    -0.07
     sevent
    -0.07
    jícím
    -0.07
     ακό
    -0.06
    ển
    -0.06
    .plan
    -0.06
    mesine
    -0.06
    Mono
    -0.06
     hentai
    -0.06
    POSITIVE LOGITS
     Count
    0.06
     Safe
    0.06
     dissent
    0.06
     Fraction
    0.06
    letal
    0.06
     Afghanistan
    0.06
     Definitely
    0.06
     permissions
    0.06
     ALL
    0.06
     administrator
    0.06
    Act Density 0.000%

    No Known Activations