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

    Neuronpedia

    INDEX
    Explanations

    contractions and auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [
    -0.07
    ENN
    -0.07
    apor
    -0.07
     oraz
    -0.06
    лаг
    -0.06
    _VALUES
    -0.06
    악
    -0.06
     Fine
    -0.06
    ox
    -0.06
     Memory
    -0.06
    POSITIVE LOGITS
    ++++
    0.06
     діяльність
    0.06
    _player
    0.06
    ':{'
    0.06
    _printer
    0.06
    jni
    0.06
    """
↵
↵
    0.06
    _https
    0.06
    璃
    0.06
    _sigma
    0.06
    Act Density 0.087%

    No Known Activations