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

    Neuronpedia

    INDEX
    Explanations

    angular

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     travers
    -0.08
    ↵  ↵
    -0.08
     فهو
    -0.07
     forest
    -0.07
    .nb
    -0.07
    ㎢
    -0.07
    =c
    -0.07
     foods
    -0.07
    ᥔ
    -0.07
    𝖘
    -0.07
    POSITIVE LOGITS
    מונים
    0.07
    헐
    0.07
    웩
    0.07
    ﭹ
    0.07
     giochi
    0.07
    ตาร
    0.07
    polator
    0.06
    表演
    0.06
    试试
    0.06
     deceive
    0.06
    Act Density 0.001%

    No Known Activations