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

    Neuronpedia

    INDEX
    Explanations

    currency symbols and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    læ
    0.47
    nomes
    0.45
    all
    0.45
    ant
    0.43
    so
    0.43
    ala
    0.41
    eli
    0.41
     Prot
    0.41
    aju
    0.41
    alls
    0.41
    POSITIVE LOGITS
    ICEF
    0.48
    tembre
    0.43
    Specified
    0.42
    Terms
    0.40
    もある
    0.40
    TRAS
    0.39
    dS
    0.39
    EDA
    0.38
    ITC
    0.38
    वायरमेंट
    0.38
    Act Density 0.001%

    No Known Activations