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

    Neuronpedia

    INDEX
    Explanations

    Further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uforia
    -0.07
    уются
    -0.06
     Dispatcher
    -0.06
    (activity
    -0.06
     yarat
    -0.06
     striving
    -0.06
    _PREVIEW
    -0.06
    .unsubscribe
    -0.06
    ety
    -0.06
    matrix
    -0.06
    POSITIVE LOGITS
    岳
    0.07
    =forms
    0.07
    그
    0.07
    _SEC
    0.06
     χώ
    0.06
    _definition
    0.06
    _Att
    0.06
     kindly
    0.06
    Further
    0.06
    ;:;:;:;:
    0.06
    Act Density 0.006%

    No Known Activations