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

    Neuronpedia

    INDEX
    Explanations

    Polish language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /pay
    -0.07
    _er
    -0.06
    _N
    -0.06
    umu
    -0.06
     Priv
    -0.06
    .Usuario
    -0.06
    улю
    -0.06
     antiqu
    -0.06
    िण
    -0.05
    (media
    -0.05
    POSITIVE LOGITS
     decrypt
    0.07
     Scarlett
    0.06
    iễn
    0.06
    jong
    0.06
     фун
    0.06
     Bron
    0.06
    abee
    0.06
    iggs
    0.06
     StringField
    0.06
    AMY
    0.06
    Act Density 0.097%

    No Known Activations