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

    Neuronpedia

    INDEX
    Explanations

    horizontal line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	fill
    -0.08
    كل
    -0.07
    leriyle
    -0.07
    ellite
    -0.07
    -middle
    -0.07
    ############################################################
    -0.07
    应该
    -0.07
    يلاد
    -0.06
    esiyle
    -0.06
    광역시
    -0.06
    POSITIVE LOGITS
    ────
    0.06
     �
    0.06
    ──
    0.06
    .rdf
    0.06
    ────────
    0.06
    riculum
    0.06
     ingredients
    0.06
    .Func
    0.06
    �
    0.06
     won
    0.06
    Act Density 0.002%

    No Known Activations