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

    Neuronpedia

    INDEX
    Explanations

    academic, optimization, assembly, secretary, public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olisme
    0.40
     allow
    0.39
    \|\
    0.39
     Cassie
    0.38
     Scrap
    0.37
    زا
    0.37
    க்கார
    0.36
    堈
    0.36
    idente
    0.35
    subMenu
    0.35
    POSITIVE LOGITS
    ुओं
    0.42
    nament
    0.41
    ping
    0.40
     académico
    0.40
     pavil
    0.40
     académicos
    0.39
    aces
    0.38
     edific
    0.38
    vesti
    0.38
    estamps
    0.38
    Act Density 0.000%

    No Known Activations