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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    housing
    -0.07
    クロ
    -0.06
    图
    -0.06
    _space
    -0.06
    :Event
    -0.06
    -reported
    -0.06
     повтор
    -0.06
    LiveData
    -0.06
    culos
    -0.06
    ("="
    -0.06
    POSITIVE LOGITS
    ugo
    0.06
    activ
    0.06
    _be
    0.06
    andid
    0.06
     discomfort
    0.05
     concede
    0.05
    !’
    0.05
    痛
    0.05
    _PI
    0.05
     واح
    0.05
    Act Density 0.183%

    No Known Activations