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

    Neuronpedia

    INDEX
    Explanations

    capping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creatively
    -0.06
    /global
    -0.06
     forcing
    -0.06
     par
    -0.06
    onec
    -0.06
    ,
↵
    -0.06
    ainties
    -0.05
    ATOR
    -0.05
    fail
    -0.05
    ES
    -0.05
    POSITIVE LOGITS
     capped
    0.19
    apped
    0.10
    apping
    0.09
    чины
    0.07
     xử
    0.07
    かり
    0.07
     tslib
    0.07
    Translated
    0.07
     matched
    0.07
    重複
    0.06
    Act Density 0.009%

    No Known Activations