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

    Neuronpedia

    INDEX
    Explanations

    a or A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    챃
    -0.07
    argv
    -0.07
    خم
    -0.07
    طرح
    -0.06
     가치
    -0.06
     Dũng
    -0.06
    ಛ
    -0.06
    DOM
    -0.06
     value
    -0.06
    יזם
    -0.06
    POSITIVE LOGITS
     fool
    0.07
     vidéos
    0.07
    就近
    0.07
     Lis
    0.07
     analogy
    0.07
    😂
    0.06
     Neh
    0.06
    遭到
    0.06
    paging
    0.06
     Klo
    0.06
    Act Density 0.069%

    No Known Activations