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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    weekly
    -0.06
    Scripts
    -0.06
    �
    -0.06
    -vertical
    -0.06
    Filters
    -0.06
     деся
    -0.06
    _gift
    -0.06
    AZ
    -0.06
    declspec
    -0.06
     aument
    -0.06
    POSITIVE LOGITS
    ()?.
    0.07
     pressed
    0.06
    -turned
    0.06
     μέσα
    0.06
     افراد
    0.06
     screamed
    0.06
     underst
    0.06
    :")↵
    0.06
    _encoding
    0.06
     Require
    0.06
    Act Density 0.016%

    No Known Activations