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

    Neuronpedia

    INDEX
    Explanations

    duplicated letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    473
    -0.07
     Cres
    -0.07
    xpath
    -0.06
    Ingredients
    -0.06
    ers
    -0.06
    cue
    -0.06
    宣
    -0.06
    “When
    -0.06
    fails
    -0.06
     ремон
    -0.06
    POSITIVE LOGITS
    .dd
    0.07
     более
    0.06
     OMAP
    0.06
    Occup
    0.06
    发行
    0.06
    pai
    0.06
    (ii
    0.06
    海
    0.06
     Benn
    0.06
    ellt
    0.06
    Act Density 0.041%

    No Known Activations