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

    Neuronpedia

    INDEX
    Explanations

    Protocols handle, often associated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     মুহাম্মদ
    0.49
    e
    0.47
     മുഹമ്മ
    0.45
    경
    0.45
    Θ
    0.45
    i
    0.45
    OS
    0.44
     metabolism
    0.44
    FileSystem
    0.44
    ーん
    0.44
    POSITIVE LOGITS
     коммента
    0.43
     reli
    0.42
     самы
    0.42
     посвящен
    0.42
     devoting
    0.42
    CUIT
    0.42
     привле
    0.41
    цами
    0.41
     Gou
    0.41
     Coker
    0.41
    Act Density 0.003%

    No Known Activations