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

    Neuronpedia

    INDEX
    Explanations

    vicuna language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nhold
    0.76
    log
    0.71
     Clo
    0.67
    зывает
    0.66
     ဆ
    0.65
    Stdout
    0.65
     |-
    0.64
    px
    0.63
    STO
    0.63
     Bayes
    0.63
    POSITIVE LOGITS
    肐
    0.78
    較
    0.78
    睢
    0.76
     menjel
    0.72
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.69
     डिग्री
    0.68
    गीय
    0.67
     इंडियन
    0.67
    逘
    0.67
    ulph
    0.67
    Act Density 0.001%

    No Known Activations