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

    Neuronpedia

    INDEX
    Explanations

    how things resonate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourselves
    0.44
    WEEN
    0.41
    配合
    0.40
     ifstream
    0.40
     yourself
    0.39
    watercolor
    0.39
    кә
    0.38
     lindo
    0.38
    Anthrop
    0.38
    注目
    0.38
    POSITIVE LOGITS
     resonated
    0.71
     resonates
    0.70
     resonate
    0.70
     resonance
    0.62
     reson
    0.61
     resonant
    0.60
     Resonance
    0.56
     landing
    0.55
    resonance
    0.52
     Landing
    0.49
    Act Density 0.015%

    No Known Activations