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

    Neuronpedia

    INDEX
    Explanations

    emphasis on specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flew
    0.34
     benutzt
    0.32
     onto
    0.32
     Using
    0.31
    0.31
     into
    0.31
     took
    0.30
     durch
    0.30
     cautiously
    0.30
     curiously
    0.29
    POSITIVE LOGITS
     особенно
    0.50
     especially
    0.46
    Especially
    0.46
    특히
    0.46
    especially
    0.44
    特に
    0.44
     особливо
    0.44
     खासकर
    0.42
     although
    0.42
     meskipun
    0.40
    Act Density 0.303%

    No Known Activations