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

    Neuronpedia

    INDEX
    Explanations

    ut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROY
    -0.07
    .trans
    -0.07
    .jackson
    -0.07
     defeating
    -0.07
    alendar
    -0.07
    quiry
    -0.06
    Pane
    -0.06
    Playlist
    -0.06
    [this
    -0.06
    Operating
    -0.06
    POSITIVE LOGITS
     ↑
    0.08
     качества
    0.06
    پس
    0.06
    组织
    0.06
    _empresa
    0.06
    :The
    0.06
     місця
    0.06
    -slot
    0.06
    	code
    0.06
    ━━━━━━━━━━━━━━━━
    0.06
    Act Density 0.028%

    No Known Activations