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

    Neuronpedia

    INDEX
    Explanations

    Gemma LLaMA model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cartesian
    0.57
     Rec
    0.48
     Pokemon
    0.47
     appeal
    0.45
    ہ
    0.45
    ہر
    0.45
     jungen
    0.45
    修炼
    0.44
     Mis
    0.44
     Fru
    0.44
    POSITIVE LOGITS
    tz
    0.52
    enzyme
    0.50
     GX
    0.47
    arettes
    0.47
    laboratory
    0.46
    KURZ
    0.45
    াট
    0.45
    audience
    0.44
    세요
    0.44
    izziness
    0.44
    Act Density 0.001%

    No Known Activations