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

    Neuronpedia

    INDEX
    Explanations

    critical statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (valor
    -0.07
    .tar
    -0.07
    _TERM
    -0.06
    utral
    -0.06
    .Button
    -0.06
     نشر
    -0.06
    66
    -0.06
    etten
    -0.06
    (PORT
    -0.06
     oranges
    -0.06
    POSITIVE LOGITS
     endregion
    0.07
    *******/↵↵
    0.06
    _does
    0.06
    lbrace
    0.06
     uneven
    0.06
     tutoring
    0.06
    redi
    0.06
    لات
    0.06
     unst
    0.06
     alt
    0.06
    Act Density 0.046%

    No Known Activations