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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sao
    -0.07
    ZH
    -0.07
    Login
    -0.06
    -sh
    -0.06
    iger
    -0.06
    -fired
    -0.06
    .bind
    -0.06
    death
    -0.06
    matchCondition
    -0.06
     harga
    -0.06
    POSITIVE LOGITS
    นะ
    0.06
     Podesta
    0.06
     disjoint
    0.06
     공부
    0.06
    址
    0.06
    (Void
    0.06
    프로
    0.06
     Screw
    0.06
     tenemos
    0.06
     nedost
    0.06
    Act Density 0.032%

    No Known Activations