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

    Neuronpedia

    INDEX
    Explanations

    legal disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ߘ
    -0.08
     Artikel
    -0.07
     Rd
    -0.07
    过往
    -0.07
     SOC
    -0.07
     persone
    -0.06
    泅
    -0.06
    ꒪
    -0.06
    耵
    -0.06
    ขยาย
    -0.06
    POSITIVE LOGITS
     coal
    0.07
    y
    0.07
    .y
    0.07
    Area
    0.07
    cheap
    0.07
    empl
    0.07
     malignant
    0.07
    .blocks
    0.07
    三农
    0.07
    芦
    0.07
    Act Density 0.010%

    No Known Activations