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

    Neuronpedia

    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ren
    -0.07
    露天
    -0.07
    睹
    -0.07
    赞助
    -0.07
    �
    -0.07
    irm
    -0.07
     contradiction
    -0.07
    场地
    -0.06
    \Dependency
    -0.06
    ch
    -0.06
    POSITIVE LOGITS
    提出了
    0.07
     BOOT
    0.07
    >I
    0.07
    𨟠
    0.07
    finalize
    0.06
     Kaz
    0.06
    hee
    0.06
    кал
    0.06
    icators
    0.06
    ума
    0.06
    Act Density 0.004%

    No Known Activations