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

    Neuronpedia

    INDEX
    Explanations

    General text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     распред
    -0.07
    .closest
    -0.07
    ンバー
    -0.07
     họp
    -0.06
     हट
    -0.06
     wi
    -0.06
     khí
    -0.06
    ob
    -0.06
    ноч
    -0.06
     racer
    -0.06
    POSITIVE LOGITS
     planted
    0.07
    .Checked
    0.06
    consistent
    0.06
    (te
    0.06
     declaring
    0.06
     Celt
    0.06
    ）。↵
    0.06
    -book
    0.06
    _past
    0.06
     expressing
    0.06
    Act Density 0.000%

    No Known Activations