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

    Neuronpedia

    INDEX
    Explanations

    accretion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cpp
    -0.08
     cafes
    -0.07
     rpt
    -0.07
    新媒体
    -0.07
     Fetish
    -0.07
    🔝
    -0.07
    (pointer
    -0.07
    🦠
    -0.07
     опцион
    -0.07
     GHC
    -0.07
    POSITIVE LOGITS
    じゃ
    0.08
    有利于
    0.07
    赐
    0.07
     וב
    0.07
     compromise
    0.07
    ớ
    0.07
    _family
    0.07
    .','
    0.07
    osing
    0.07
    并向
    0.06
    Act Density 0.012%

    No Known Activations