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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raj
    -0.07
     реж
    -0.06
    _review
    -0.06
     slip
    -0.06
     maple
    -0.06
     reopen
    -0.06
     Nap
    -0.06
     Pass
    -0.06
    (identity
    -0.06
     durations
    -0.06
    POSITIVE LOGITS
     některých
    0.07
     getUsername
    0.07
     thanking
    0.07
     FAMILY
    0.06
    orman
    0.06
    GetPosition
    0.06
    Cancellation
    0.06
    Quaternion
    0.06
    گاهی
    0.06
    .statistics
    0.06
    Act Density 0.012%

    No Known Activations