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

    Neuronpedia

    INDEX
    Explanations

    improvisation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    겉
    0.41
    tailwind
    0.38
     демон
    0.38
    разуме
    0.38
     ballistic
    0.38
     полю
    0.37
     চোখ
    0.37
     thermique
    0.37
     camphor
    0.37
    compound
    0.36
    POSITIVE LOGITS
     improvis
    1.59
     improv
    1.55
     improvisation
    1.49
    improv
    1.48
     sketch
    1.38
     improvised
    1.38
     Impro
    1.33
     impro
    1.31
    Sketch
    1.21
    sketch
    1.18
    Act Density 0.016%

    No Known Activations