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
    Cooldown
    -0.08
    Nb
    -0.06
     fie
    -0.06
     ziyaret
    -0.06
     babes
    -0.06
     almacen
    -0.06
     Be
    -0.06
     haya
    -0.06
     регулю
    -0.06
    KS
    -0.06
    POSITIVE LOGITS
    pak
    0.06
    犯
    0.06
     detailed
    0.06
     �
    0.06
     ij
    0.06
    ANC
    0.06
     JAXB
    0.06
     введ
    0.06
    :C
    0.06
     Papua
    0.06
    Act Density 0.001%

    No Known Activations