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

    Neuronpedia

    INDEX
    Explanations

    SQL queries with conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Az
    0.55
     Wool
    0.52
     Chang
    0.51
     Jes
    0.50
     Netflix
    0.47
     Ol
    0.47
     Bog
    0.47
     Pop
    0.47
     Clement
    0.47
     City
    0.46
    POSITIVE LOGITS
     conditionals
    0.55
     validations
    0.50
     analogies
    0.49
     competency
    0.48
     vít
    0.46
     randomization
    0.46
    偻
    0.45
    μ
    0.45
    difficulty
    0.44
    factorial
    0.44
    Act Density 0.000%

    No Known Activations