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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gu
    -0.07
    .started
    -0.07
    เฉ
    -0.07
     timeval
    -0.06
     manga
    -0.06
     spilled
    -0.06
    enson
    -0.06
     sightings
    -0.06
    егодня
    -0.06
    aco
    -0.06
    POSITIVE LOGITS
    -fixed
    0.06
    /con
    0.06
    setStatus
    0.06
    ]+
    0.06
    /em
    0.06
    ơ
    0.06
    ";
    0.06
    moving
    0.06
    =*/
    0.06
     warns
    0.05
    Act Density 0.031%

    No Known Activations