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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alo
    -0.06
     Kay
    -0.06
     classifiers
    -0.06
    racak
    -0.06
     Astros
    -0.06
     halo
    -0.06
    ouv
    -0.06
    /c
    -0.06
     bul
    -0.06
     constraints
    -0.06
    POSITIVE LOGITS
    =title
    0.07
    fileName
    0.07
    perienced
    0.07
     tranh
    0.06
    業務
    0.06
     يع
    0.06
    业务
    0.06
     promptly
    0.06
    .dynamic
    0.06
     }
↵
↵
↵
↵
    0.06
    Act Density 0.006%

    No Known Activations