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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    发展
    -0.07
     cht
    -0.07
     फै
    -0.07
     Stem
    -0.07
    roof
    -0.07
    ево
    -0.07
     dominate
    -0.07
     plaisir
    -0.07
     instagram
    -0.07
     connective
    -0.07
    POSITIVE LOGITS
     malicious
    0.12
     victime
    0.10
    Forgery
    0.10
     corrective
    0.10
    severity
    0.10
     Correction
    0.10
     correction
    0.10
     difference
    0.10
    Difference
    0.10
     faulty
    0.10
    Act Density 0.038%

    No Known Activations