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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponential
    -0.07
    74
    -0.07
    asses
    -0.06
    aves
    -0.06
     Hermes
    -0.06
     mim
    -0.06
    ede
    -0.06
    irá
    -0.06
    ighton
    -0.06
    uitka
    -0.06
    POSITIVE LOGITS
     Zhou
    0.06
     ort
    0.06
    TRY
    0.06
    /mp
    0.06
     vom
    0.06
     trest
    0.06
     obl
    0.06
     Proceed
    0.06
     storyline
    0.06
    	ui
    0.06
    Act Density 0.114%

    No Known Activations