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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    งของ
    -0.07
    _IO
    -0.07
     Potato
    -0.06
     theres
    -0.06
    abling
    -0.06
    €€
    -0.06
     Buffy
    -0.06
     ثابت
    -0.06
    (t
    -0.06
    _cc
    -0.06
    POSITIVE LOGITS
     your
    0.08
     fearless
    0.08
    ै
    0.07
    -Mail
    0.07
    icion
    0.06
    Your
    0.06
    ISED
    0.06
     nostra
    0.06
    肩
    0.06
    별
    0.06
    Act Density 0.055%

    No Known Activations