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

    Neuronpedia

    INDEX
    Explanations

    logical argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invers
    -0.10
    sudo
    -0.09
     Satoshi
    -0.09
     Sylvia
    -0.09
     Sphinx
    -0.09
    å±¥
    -0.09
    -str
    -0.09
     Santiago
    -0.08
     fatt
    -0.08
    sensor
    -0.08
    POSITIVE LOGITS
     S
    0.23
    =S
    0.19
    (S
    0.16
     s
    0.16
    "S
    0.15
    :S
    0.15
    \tS
    0.14
    .getS
    0.14
    .S
    0.13
    ,S
    0.13
    Act Density 0.263%

    No Known Activations