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

    Neuronpedia

    INDEX
    Explanations

    gauge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    consin
    -0.06
     각각
    -0.06
     توص
    -0.06
     Wanna
    -0.06
    ΤΙΚ
    -0.06
     خم
    -0.06
    Ζ
    -0.06
     underwear
    -0.06
     спор
    -0.06
     célib
    -0.06
    POSITIVE LOGITS
    】,【
    0.07
    394
    0.06
    ldkf
    0.06
    _requests
    0.06
    izzlies
    0.06
    Amount
    0.06
    imestone
    0.06
     mirrors
    0.06
     len
    0.06
    (provider
    0.06
    Act Density 0.155%

    No Known Activations