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

    Neuronpedia

    INDEX
    Explanations

    analogy and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resonant
    0.35
     suggest
    0.32
    觴
    0.31
     poes
    0.31
     ibis
    0.30
     minimalistic
    0.30
     cache
    0.30
     turbine
    0.30
     بخشی
    0.30
     peruse
    0.30
    POSITIVE LOGITS
    образ
    0.43
    みたいな
    0.37
    似的
    0.37
     analogy
    0.35
     паспо
    0.35
    или
    0.34
     territoires
    0.34
    Like
    0.33
    Си
    0.33
    like
    0.32
    Act Density 0.579%

    No Known Activations