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

    Neuronpedia

    INDEX
    Explanations

    injection, ignition, propulsion, encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spectre
    0.39
    ot
    0.36
     curiosity
    0.36
     spectator
    0.35
    łość
    0.34
     hemorrhagic
    0.34
    ong
    0.33
     NSFW
    0.33
     malfunctioning
    0.32
     tasse
    0.32
    POSITIVE LOGITS
    ra
    0.55
    se
    0.50
    1
    0.47
    ti
    0.47
    một
    0.44
    titles
    0.44
    ব
    0.43
    ب
    0.43
    la
    0.42
     üç
    0.42
    Act Density 0.046%

    No Known Activations