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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERROR
    -0.07
     papel
    -0.07
     cargo
    -0.07
    -sale
    -0.06
    Haz
    -0.06
    ustainability
    -0.06
    C
    -0.06
    İTESİ
    -0.06
     Ey
    -0.06
     supermarkets
    -0.06
    POSITIVE LOGITS
    (ph
    0.07
    xon
    0.07
    加工
    0.07
    isdiction
    0.06
     зависим
    0.06
    �
    0.06
     -*-
↵
    0.06
     Terms
    0.06
     ballistic
    0.06
    らせ
    0.06
    Act Density 0.004%

    No Known Activations