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

    Neuronpedia

    INDEX
    Explanations

    virtwifi, Videvo, autostart, vers=3.0, Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    एं
    2.15
    ে
    2.08
    herent
    2.02
    ेबल
    1.97
    amps
    1.89
    hood
    1.88
     tomado
    1.87
    প্তাহ
    1.87
    ரியா
    1.81
     направ
    1.80
    POSITIVE LOGITS
    u
    3.60
    ка
    3.01
    on
    2.90
    in
    2.66
    el
    2.63
    m
    2.60
    n
    2.57
    ie
    2.40
    م
    2.34
    r
    2.31
    Act Density 0.049%

    No Known Activations