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

    Neuronpedia

    INDEX
    Explanations

    importing nim modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Authorized
    0.42
    અ
    0.39
     холо
    0.39
    വ്
    0.38
     Regl
    0.38
    ਜ਼
    0.38
    怀孕
    0.37
    ということ
    0.37
     मुताब
    0.37
     ovviamente
    0.36
    POSITIVE LOGITS
    due
    0.37
     Gottfried
    0.37
     Abdel
    0.37
     Aeonium
    0.37
    illes
    0.37
    Due
    0.36
     spin
    0.36
     sapphire
    0.36
    Gpio
    0.35
     nhiêu
    0.35
    Act Density 0.003%

    No Known Activations