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

    Neuronpedia

    INDEX
    Explanations

    uclear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     weary
    -0.07
     Clown
    -0.07
     besten
    -0.06
    ITTE
    -0.06
     florida
    -0.06
     cosine
    -0.06
     Dollar
    -0.06
     мінім
    -0.06
    _step
    -0.06
    POSITIVE LOGITS
     nuclear
    0.17
    uclear
    0.13
     Nuclear
    0.13
     nuclei
    0.09
     Vanderbilt
    0.08
     핵
    0.08
     nucleus
    0.07
    ЮЛ
    0.07
     UT
    0.07
    خ
    0.07
    Act Density 0.008%

    No Known Activations