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

    Neuronpedia

    INDEX
    Explanations

    Ro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    จน
    -0.07
     dok
    -0.07
    施
    -0.07
    咨询
    -0.07
     simpl
    -0.07
    serve
    -0.07
    .notNull
    -0.07
     candidate
    -0.07
    是有
    -0.07
     kron
    -0.07
    POSITIVE LOGITS
    bookmark
    0.07
    切入点
    0.07
    𝓲
    0.07
    配电
    0.07
    harma
    0.07
    	begin
    0.07
    يمة
    0.06
    ᅬ
    0.06
     guessed
    0.06
    _arc
    0.06
    Act Density 0.011%

    No Known Activations