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

    Neuronpedia

    INDEX
    Explanations

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bö
    -0.07
    Fa
    -0.06
    ещ
    -0.06
    _half
    -0.06
     �
    -0.06
    iado
    -0.06
    appy
    -0.06
     Permission
    -0.06
    acin
    -0.06
     None
    -0.06
    POSITIVE LOGITS
    öyle
    0.07
    ОВ
    0.07
    spe
    0.07
    -controls
    0.07
     ailments
    0.07
     началь
    0.06
     ArgumentError
    0.06
    -тех
    0.06
    racak
    0.06
    ogy
    0.06
    Act Density 0.009%

    No Known Activations