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

    Neuronpedia

    INDEX
    Explanations

    IPO, tasks, income, upstairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     r
    0.48
     efficacy
    0.46
     ac
    0.42
     incon
    0.42
     ruch
    0.41
     he
    0.41
     i
    0.41
     o
    0.40
     badania
    0.40
     oryginal
    0.40
    POSITIVE LOGITS
    qués
    0.46
    VCTarget
    0.46
    㨁
    0.44
    ਕੇ
    0.43
    oleč
    0.43
    DeleteItem
    0.42
    ल्ड
    0.42
    Podcast
    0.42
    ᓛ
    0.42
     disappointed
    0.42
    Act Density 0.001%

    No Known Activations