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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ritual
    -0.07
    _CONSTANT
    -0.06
    犬
    -0.06
     Cic
    -0.06
     burnt
    -0.06
     Chlor
    -0.06
    対応
    -0.06
     Crushers
    -0.06
    Carol
    -0.06
     Cleaner
    -0.06
    POSITIVE LOGITS
     ami
    0.07
    '',
    0.06
     tee
    0.06
    ulla
    0.06
     activism
    0.06
    _ms
    0.06
    _ask
    0.06
    รษฐ
    0.06
    _us
    0.06
    .accuracy
    0.06
    Act Density 0.024%

    No Known Activations