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

    Neuronpedia

    INDEX
    Explanations

    sharing notes or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anyone
    0.83
     Anything
    0.79
     bárm
    0.74
     اقتص
    0.73
    𝙲
    0.72
     Alfa
    0.72
     Bibliothe
    0.72
     come
    0.71
     بار
    0.71
     Такой
    0.70
    POSITIVE LOGITS
     notes
    0.74
    NOTE
    0.69
     votos
    0.69
     NOTE
    0.66
    ikes
    0.63
     note
    0.63
    university
    0.63
     noted
    0.63
    college
    0.62
     users
    0.61
    Act Density 0.000%

    No Known Activations