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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deg
    -0.07
    ощи
    -0.06
     trapping
    -0.06
     المو
    -0.06
    HOOK
    -0.06
     minutos
    -0.06
     Than
    -0.06
     TIME
    -0.06
    .UUID
    -0.06
    Than
    -0.06
    POSITIVE LOGITS
    接着
    0.07
    ична
    0.06
    ồi
    0.06
    ают
    0.06
    aný
    0.06
    atıcı
    0.06
     переп
    0.06
    ?action
    0.06
    communications
    0.06
     alanında
    0.06
    Act Density 0.008%

    No Known Activations