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

    Neuronpedia

    INDEX
    Explanations

    diffusion models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ců
    0.41
    ười
    0.40
    🇷
    0.38
    PluginResult
    0.38
     ஒப்பந்த
    0.37
    ilities
    0.37
     Manc
    0.37
    CodeDom
    0.36
     पेमेंट
    0.36
    писать
    0.35
    POSITIVE LOGITS
     предше
    0.41
    fp
    0.38
     accompany
    0.38
    âm
    0.37
     ar
    0.37
    zesz
    0.36
     앞
    0.36
     cfp
    0.36
     dp
    0.36
    agna
    0.36
    Act Density 0.000%

    No Known Activations