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

    Neuronpedia

    INDEX
    Explanations

    cannot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yd
    -0.07
    ossed
    -0.07
     s
    -0.07
     hype
    -0.07
    d
    -0.07
    4
    -0.07
     med
    -0.06
     read
    -0.06
    y
    -0.06
    3
    -0.06
    POSITIVE LOGITS
     cannot
    0.14
    cannot
    0.12
     Cannot
    0.12
    Cannot
    0.10
    ANNOT
    0.10
    not
    0.09
    amon
    0.09
    NOT
    0.08
    _CANNOT
    0.08
    annot
    0.08
    Act Density 0.015%

    No Known Activations