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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     "(
    -0.06
     RM
    -0.06
    ohana
    -0.06
     Romantic
    -0.06
    _TERM
    -0.06
     ※
    -0.06
     Jurassic
    -0.06
     resonate
    -0.06
    -tank
    -0.06
    POSITIVE LOGITS
     veterans
    0.07
     بیمار
    0.06
    [Any
    0.06
     Philosophy
    0.06
    _RING
    0.06
    نتی
    0.06
     необходимо
    0.06
    nutí
    0.06
     Aero
    0.06
     eng
    0.06
    Act Density 0.021%

    No Known Activations