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

    Neuronpedia

    INDEX
    Explanations

    code and math separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৭০
    0.76
    ৪০
    0.69
    ৬০
    0.69
    ৬৫
    0.69
    ৫৫
    0.69
    ৩
    0.68
    ৬
    0.64
    ৩৫
    0.64
    ৫
    0.63
    ৫০
    0.63
    POSITIVE LOGITS
    sonian
    0.65
     Hegel
    0.61
     Crimea
    0.59
     someday
    0.56
     yolk
    0.55
     Lenin
    0.54
     Marxist
    0.54
     felony
    0.54
     Verse
    0.54
     liv
    0.54
    Act Density 0.172%

    No Known Activations