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

    Neuronpedia

    INDEX
    Explanations

    all star by Smash Mouth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     videos
    0.74
     video
    0.71
     prioritizing
    0.68
     subs
    0.66
     prioritize
    0.66
    castle
    0.65
     contrib
    0.64
     bust
    0.63
     Conventions
    0.63
     वीडियो
    0.63
    POSITIVE LOGITS
    ronidazole
    0.86
    Butyl
    0.83
     바로
    0.83
    መሳሳይ
    0.82
     உம்
    0.78
    Neurons
    0.77
     ശ്രമ
    0.77
     herbicide
    0.76
    ₲
    0.76
     මේ
    0.76
    Act Density 0.124%

    No Known Activations