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

    Neuronpedia

    INDEX
    Explanations

    Hugging Face

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilation
    0.50
     malo
    0.49
    imaan
    0.46
    ndon
    0.45
    ilty
    0.44
    쑥
    0.44
    quisition
    0.44
    varlak
    0.44
     sợ
    0.43
    ሏ
    0.43
    POSITIVE LOGITS
    transformers
    0.84
     Transformers
    0.84
     Hug
    0.81
     transformers
    0.79
    Transformers
    0.76
     hugging
    0.74
     hug
    0.72
    Hughes
    0.71
    🤗
    0.71
     Face
    0.70
    Act Density 0.013%

    No Known Activations