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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phong
    -0.07
     paralyzed
    -0.06
     LED
    -0.06
    Pot
    -0.06
     new
    -0.06
     Duncan
    -0.06
     Pol
    -0.06
     gad
    -0.06
     dra
    -0.06
    appl
    -0.06
    POSITIVE LOGITS
    âte
    0.06
     allele
    0.06
    estation
    0.06
    Lemma
    0.06
    .summary
    0.06
    (proc
    0.06
     Chiến
    0.06
    emploi
    0.06
     سخن
    0.06
    avic
    0.06
    Act Density 0.018%

    No Known Activations