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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nú
    -0.08
     Rapid
    -0.08
     Macro
    -0.07
     ).↵↵
    -0.07
     pesticides
    -0.07
    (MenuItem
    -0.07
     budget
    -0.07
    ystore
    -0.07
    Measurement
    -0.06
    unar
    -0.06
    POSITIVE LOGITS
    nop
    0.07
    راحة
    0.07
     Klopp
    0.07
     violate
    0.07
    rollback
    0.06
    俜
    0.06
    伊斯兰
    0.06
    没了
    0.06
    грамм
    0.06
    -transparent
    0.06
    Act Density 0.003%

    No Known Activations