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

    Neuronpedia

    INDEX
    Explanations

    Adjustable arms/stands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spaces
    -0.07
    ecek
    -0.07
    しい
    -0.06
    ...↵
    -0.06
    sek
    -0.06
     ≥
    -0.06
     nhạc
    -0.06
     rises
    -0.06
     LORD
    -0.06
     뒤
    -0.06
    POSITIVE LOGITS
    _ARM
    0.08
     Bảo
    0.07
    displayName
    0.06
    ็นการ
    0.06
    dı
    0.06
     Cyprus
    0.06
    entimes
    0.06
     Jame
    0.06
    _closure
    0.06
     Assign
    0.06
    Act Density 0.061%

    No Known Activations