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

    Neuronpedia

    INDEX
    Explanations

    functions, vocab, Lib, 7, Dominant, Objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.50
    pl
    0.46
    krit
    0.43
    ART
    0.41
    TT
    0.41
     Bhutan
    0.41
    hljs
    0.40
    Ng
    0.40
    BF
    0.40
    Subject
    0.40
    POSITIVE LOGITS
     অনার্স
    0.51
    餸
    0.48
    ამდე
    0.47
    ্যান্স
    0.46
    呷
    0.45
    вина
    0.44
    ባቸው
    0.44
    ين
    0.44
     babys
    0.43
     pinched
    0.42
    Act Density 0.003%

    No Known Activations