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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    0
    -0.07
     ο
    -0.06
    ,O
    -0.06
     ソ
    -0.06
    、お
    -0.06
     Oh
    -0.06
    QWidget
    -0.06
    '.$
    -0.06
     Mark
    -0.06
    'o
    -0.06
    POSITIVE LOGITS
     between
    0.27
    between
    0.22
     Between
    0.21
    Between
    0.18
     BETWEEN
    0.17
    -between
    0.13
     tussen
    0.12
    _between
    0.12
     zwischen
    0.11
    etween
    0.11
    Act Density 0.064%

    No Known Activations