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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ूल
    -0.07
    ű
    -0.07
    PLAN
    -0.07
     Jury
    -0.06
     Králové
    -0.06
     Pf
    -0.06
    에서는
    -0.06
    ोद
    -0.06
    Cx
    -0.06
     찬
    -0.06
    POSITIVE LOGITS
    /thumb
    0.07
    	buffer
    0.07
     forty
    0.07
     disappear
    0.07
     FOOD
    0.06
     bib
    0.06
     alright
    0.06
     bombed
    0.06
    ofilm
    0.06
     bulld
    0.06
    Act Density 0.000%

    No Known Activations