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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rejo
    -0.07
     Για
    -0.07
     containing
    -0.07
     внутріш
    -0.06
    (da
    -0.06
     rainbow
    -0.06
    _avail
    -0.06
    _neurons
    -0.06
    $row
    -0.06
    ního
    -0.06
    POSITIVE LOGITS
    glich
    0.06
     utrecht
    0.06
    usk
    0.06
    arie
    0.06
    _THEME
    0.06
    CHANT
    0.06
    INY
    0.06
    .keySet
    0.06
    撤
    0.06
     finde
    0.06
    Act Density 0.020%

    No Known Activations