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

    Neuronpedia

    INDEX
    Explanations

    adverbs of degree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (concat
    -0.07
    لمات
    -0.06
    ERRY
    -0.06
     dumpster
    -0.06
     shapes
    -0.06
     arrows
    -0.06
    bins
    -0.06
    .chunk
    -0.06
    เอง
    -0.06
    اسات
    -0.06
    POSITIVE LOGITS
     JMP
    0.06
     Vault
    0.06
    ‌خ
    0.06
     se
    0.06
    phot
    0.06
    NECTION
    0.06
    /j
    0.06
     нескольких
    0.06
     更
    0.06
     thanked
    0.06
    Act Density 0.025%

    No Known Activations