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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dao
    -0.06
     Bulldogs
    -0.06
     Loc
    -0.06
     isEmpty
    -0.06
    HTTP
    -0.06
    бав
    -0.06
     intro
    -0.06
     GetComponent
    -0.06
    _MP
    -0.06
    ddit
    -0.06
    POSITIVE LOGITS
     reviewer
    0.07
     अप
    0.06
     excess
    0.06
    reesome
    0.06
    _when
    0.06
    _ADV
    0.06
     impact
    0.06
     Century
    0.06
     смог
    0.06
    _wrong
    0.06
    Act Density 0.013%

    No Known Activations