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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CRA
    -0.08
     browser
    -0.07
    nie
    -0.07
     shades
    -0.07
     ENERGY
    -0.07
     Chamber
    -0.07
    KY
    -0.07
     Cra
    -0.07
     PLAN
    -0.06
     owl
    -0.06
    POSITIVE LOGITS
     Μον
    0.07
     سابق
    0.06
     ISIL
    0.06
    _exit
    0.06
     laisse
    0.06
     seront
    0.06
     gösterir
    0.06
    イツ
    0.06
     kì
    0.05
     şimdi
    0.05
    Act Density 0.118%

    No Known Activations