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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assert
    -0.08
    из
    -0.07
     dw
    -0.07
    態度
    -0.07
    variant
    -0.07
    roz
    -0.06
     Mix
    -0.06
     vers
    -0.06
    through
    -0.06
    cow
    -0.06
    POSITIVE LOGITS
    .Logger
    0.07
    צבא
    0.07
    					↵					↵
    0.07
    Domains
    0.07
    筘
    0.07
     gates
    0.07
    .media
    0.07
     боль
    0.07
    急诊
    0.06
     League
    0.06
    Act Density 0.076%

    No Known Activations