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

    Neuronpedia

    INDEX
    Explanations

    public speaking, shooting, limited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }{\
    0.53
     }}{\
    0.49
     ваши
    0.48
     Livre
    0.47
     Ска
    0.47
     Notepad
    0.45
     napkin
    0.45
     detached
    0.45
     }}$
    0.45
    簡単に
    0.44
    POSITIVE LOGITS
    0
    0.49
    M
    0.46
    ienes
    0.46
    as
    0.46
     Kurds
    0.46
    CM
    0.44
    ines
    0.44
    there
    0.44
    of
    0.43
     restauración
    0.42
    Act Density 0.001%

    No Known Activations