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

    Neuronpedia

    INDEX
    Explanations

    codes and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hill
    0.42
     HILL
    0.42
    pcion
    0.39
     Schreib
    0.39
    ärast
    0.39
     MOS
    0.38
    Hill
    0.38
    लीटर
    0.38
    ldigt
    0.37
    淺
    0.37
    POSITIVE LOGITS
    arak
    0.41
    ཤ
    0.39
    atti
    0.38
     boycott
    0.37
    และความ
    0.37
    Ⲱ
    0.37
     yet
    0.37
     ава
    0.36
     ansi
    0.36
    Recovery
    0.36
    Act Density 0.000%

    No Known Activations