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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     выяв
    -0.07
     yaptı
    -0.07
     sanitary
    -0.07
     Venezuelan
    -0.07
     kontakte
    -0.07
    kke
    -0.06
     lesbisk
    -0.06
    олева
    -0.06
    针
    -0.06
    hower
    -0.06
    POSITIVE LOGITS
    Front
    0.07
     javascript
    0.07
    確
    0.06
     ht
    0.06
    (theta
    0.06
    í
    0.06
    tığ
    0.06
     gé
    0.06
    _option
    0.06
                        ↵
    0.06
    Act Density 0.054%

    No Known Activations