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

    Neuronpedia

    INDEX
    Explanations

    command_prefix or bot prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Heav
    0.84
    ions
    0.71
    ല്ലാം
    0.71
     solubilities
    0.70
    𝘭
    0.68
    𝗌
    0.68
     ぐらい
    0.68
     Vuk
    0.68
     Pulmonary
    0.67
     пуль
    0.67
    POSITIVE LOGITS
    НИ
    0.77
    에
    0.73
     navig
    0.72
     Σε
    0.72
    ΠΑ
    0.72
    道
    0.72
    OC
    0.71
     anv
    0.71
     bestem
    0.71
     OC
    0.71
    Act Density 0.000%

    No Known Activations