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

    Neuronpedia

    INDEX
    Explanations

    fine-tuning using ShareGPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embeddings
    0.87
     মডেল
    0.82
    Embed
    0.82
     modelos
    0.81
     Gemma
    0.79
     embedding
    0.77
     mannequin
    0.76
     zod
    0.76
     embed
    0.76
    Embedding
    0.74
    POSITIVE LOGITS
    yuan
    0.82
    ূল্যে
    0.72
    원의
    0.70
    Shivam
    0.70
     Yuan
    0.67
    閨
    0.67
     McGee
    0.66
    delt
    0.65
    ᅯ
    0.64
    0.64
    Act Density 0.162%

    No Known Activations