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

    Neuronpedia

    INDEX
    Explanations

    inviting comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elen
    0.68
     பொழுது
    0.66
    äksi
    0.66
    専門
    0.65
    人材
    0.64
    દ
    0.64
    kana
    0.64
    ρκ
    0.64
    ält
    0.64
    env
    0.63
    POSITIVE LOGITS
     comments
    2.85
     comment
    2.61
     Comments
    2.44
    comments
    2.40
    comment
    2.29
    Comments
    2.27
     Comment
    2.27
     comentarios
    2.25
     commenting
    2.24
     commentaire
    2.23
    Act Density 0.058%

    No Known Activations