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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ignKey
    -0.07
     Güvenlik
    -0.07
    .dateTime
    -0.07
     Dt
    -0.06
    _accum
    -0.06
    _master
    -0.06
    .Current
    -0.06
    ((*
    -0.06
     ל
    -0.06
     viewing
    -0.06
    POSITIVE LOGITS
    ете
    0.07
    seven
    0.06
     nervous
    0.06
     Townsend
    0.06
    уры
    0.06
    оск
    0.06
     erotica
    0.06
    sending
    0.06
    术
    0.06
    AILABLE
    0.06
    Act Density 0.133%

    No Known Activations