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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "or"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Collider
    -0.08
    行政审批
    -0.07
     justice
    -0.07
     Clown
    -0.06
    濂
    -0.06
    .closest
    -0.06
    ited
    -0.06
    cliffe
    -0.06
    .show
    -0.06
    分管
    -0.06
    POSITIVE LOGITS
    """
↵
    0.08
     scripts
    0.07
    ów
    0.07
    �
    0.07
     estudiantes
    0.06
     RM
    0.06
    """↵
    0.06
     comprar
    0.06
    ???
    0.06
    备注
    0.06
    Act Density 0.135%

    No Known Activations