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

    Neuronpedia

    INDEX
    Explanations

    list items delimited by /

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RO
    0.55
     or
    0.51
    ور
    0.51
     boul
    0.50
    ש
    0.50
     H
    0.46
     hurricane
    0.46
     bowling
    0.46
     brou
    0.45
    h
    0.44
    POSITIVE LOGITS
    सी
    0.79
    и
    0.65
    Netherlands
    0.64
    ન
    0.61
    IMPORTANT
    0.60
    एन
    0.58
    ।
    0.58
     Первая
    0.58
    Table
    0.57
    𝗠
    0.57
    Act Density 0.002%

    No Known Activations