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

    Neuronpedia

    INDEX
    Explanations

    related terms and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Note
    0.43
    免費
    0.42
    free
    0.40
    note
    0.40
     FREE
    0.39
     free
    0.37
     note
    0.37
     undisturbed
    0.36
     '+
    0.35
    gn
    0.35
    POSITIVE LOGITS
     관련
    0.47
    Related
    0.44
    Terms
    0.43
     related
    0.41
     courses
    0.41
    Ivy
    0.40
    Political
    0.40
     Terms
    0.40
    関連
    0.40
     strukt
    0.40
    Act Density 0.000%

    No Known Activations