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

    Neuronpedia

    INDEX
    Explanations

    digging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ب
    -0.07
     приня
    -0.06
     announced
    -0.06
     blok
    -0.06
    цию
    -0.06
     ступ
    -0.06
    (nx
    -0.06
    dw
    -0.06
    _att
    -0.06
    [{
    -0.06
    POSITIVE LOGITS
    '});↵
    0.07
    条件
    0.06
    ModelCreating
    0.06
    Going
    0.06
    ]';↵
    0.06
     dive
    0.06
     excav
    0.06
    _search
    0.06
    .fin
    0.06
    (Resources
    0.06
    Act Density 0.007%

    No Known Activations