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

    Neuronpedia

    INDEX
    Explanations

    (:

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     participant
    -0.07
     Armenia
    -0.07
     \"{
    -0.07
    =obj
    -0.07
     Pharmaceutical
    -0.07
     Juni
    -0.07
    ･･
    -0.07
    �
    -0.07
     Fresno
    -0.07
     phone
    -0.07
    POSITIVE LOGITS
    (pages
    0.07
    _optimizer
    0.07
    _locals
    0.07
    (il
    0.07
    _equal
    0.06
    口味
    0.06
    pageTitle
    0.06
    apeake
    0.06
    .valor
    0.06
     endlessly
    0.06
    Act Density 0.006%

    No Known Activations