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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     APC
    -0.06
    usto
    -0.06
    assi
    -0.06
     osobní
    -0.06
    inspection
    -0.06
    .Pro
    -0.06
     sarà
    -0.06
     þ
    -0.06
    More
    -0.06
    (My
    -0.06
    POSITIVE LOGITS
     rave
    0.07
     userData
    0.07
    ühl
    0.07
     شهری
    0.06
    bias
    0.06
    оза
    0.06
    Stuff
    0.06
     konus
    0.06
    داد
    0.06
    CES
    0.06
    Act Density 0.002%

    No Known Activations