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

    Neuronpedia

    INDEX
    Explanations

    you are trying to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isations
    0.25
    即可
    0.25
    ==
    0.24
     ולה
    0.24
     ይ
    0.24
     forgery
    0.24
     Knowing
    0.23
     olur
    0.23
    knowing
    0.23
    य
    0.23
    POSITIVE LOGITS
     trying
    0.45
     doing
    0.39
     reacting
    0.37
     attempting
    0.37
     পারছেন
    0.36
     making
    0.35
    trying
    0.35
     bezig
    0.33
     hoping
    0.32
     applying
    0.31
    Act Density 0.104%

    No Known Activations