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

    Neuronpedia

    INDEX
    Explanations

    prove

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _solve
    -0.06
    ]:
↵
    -0.06
    еле
    -0.06
    :
↵
    -0.06
    nych
    -0.06
    LOCITY
    -0.06
    альні
    -0.06
    with
    -0.06
    ذي
    -0.06
    těz
    -0.06
    POSITIVE LOGITS
     remains
    0.07
     subprocess
    0.07
     remained
    0.06
     Kv
    0.06
    ']↵↵↵
    0.06
     handwritten
    0.06
    ORN
    0.06
    $model
    0.06
     slang
    0.06
     appearing
    0.05
    Act Density 0.045%

    No Known Activations