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
    Patient
    -0.07
     ih
    -0.06
    .trip
    -0.06
    ality
    -0.06
     lod
    -0.06
    _proc
    -0.06
    paces
    -0.06
     outFile
    -0.06
    isch
    -0.06
    tempts
    -0.06
    POSITIVE LOGITS
    belongs
    0.07
    _after
    0.07
    衝
    0.07
     Scroll
    0.07
     embar
    0.07
     Fixes
    0.07
     forCellReuseIdentifier
    0.06
     glanced
    0.06
    metics
    0.06
    梨
    0.06
    Act Density 0.093%

    No Known Activations