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

    Neuronpedia

    INDEX
    Explanations

    Web development code/URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ESC
    -0.07
    _headers
    -0.06
    ('/
    -0.06
    รษ
    -0.06
    。如果
    -0.06
     동
    -0.06
    ukes
    -0.06
     treatments
    -0.06
    _funcs
    -0.06
    ICES
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ToLeft
    0.06
     aime
    0.06
    'name
    0.06
     jiných
    0.06
    ل
    0.06
    亦
    0.06
    subpackage
    0.06
     incentiv
    0.06
    lege
    0.05
    Act Density 0.026%

    No Known Activations