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

    Neuronpedia

    INDEX
    Explanations

    file types and formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ifstream
    0.47
     zahlreichen
    0.46
     zahlreiche
    0.42
    𒄿
    0.40
    ෘ
    0.39
     companhia
    0.39
    <unused1797>
    0.39
     coordinador
    0.38
    它可以
    0.38
     государственной
    0.38
    POSITIVE LOGITS
    /
    0.65
     type
    0.60
     types
    0.57
     /
    0.56
     style
    0.56
     elements
    0.55
     methods
    0.53
     aspects
    0.51
     vs
    0.50
     format
    0.50
    Act Density 0.009%

    No Known Activations