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

    Neuronpedia

    INDEX
    Explanations

    requiring, avoid, translation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chords
    0.45
    フレーム
    0.44
     ಎಂದು
    0.44
     attempting
    0.44
    のみ
    0.43
    ケル
    0.43
    ם
    0.41
    חים
    0.41
    として
    0.40
    তের
    0.40
    POSITIVE LOGITS
     sakura
    0.47
    ırd
    0.46
     Metaverse
    0.43
     nhấn
    0.43
     Sakura
    0.43
    leted
    0.42
     редакти
    0.42
     nanotubes
    0.42
    前后
    0.41
     Terminator
    0.41
    Act Density 0.001%

    No Known Activations