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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    words
    -0.07
    olini
    -0.06
    De
    -0.06
     faire
    -0.06
    IDE
    -0.06
    guide
    -0.06
     davon
    -0.06
    Summary
    -0.06
    оны
    -0.06
     orange
    -0.06
    POSITIVE LOGITS
    (permission
    0.07
    .pad
    0.07
    °}
    0.06
     BLL
    0.06
     sıkıntı
    0.06
     فرمان
    0.06
     fors
    0.06
     zast
    0.06
     PYTHON
    0.06
    \Validator
    0.06
    Act Density 0.238%

    No Known Activations