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

    Neuronpedia

    INDEX
    Explanations

    German

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    论
    -0.08
    懂
    -0.07
    ograd
    -0.06
     waivers
    -0.06
    論
    -0.06
    uevo
    -0.06
    _ret
    -0.06
    öy
    -0.06
     vhod
    -0.06
    516
    -0.06
    POSITIVE LOGITS
     Jeg
    0.07
    ako
    0.07
    .Take
    0.06
    atisf
    0.06
     mutlu
    0.06
    ΡΓ
    0.06
    Genres
    0.06
    šní
    0.06
    IK
    0.06
    (se
    0.06
    Act Density 0.015%

    No Known Activations