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

    Neuronpedia

    INDEX
    Explanations

    topics and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DI
    0.49
     🥰
    0.47
     SM
    0.45
    🤍
    0.44
     DIGITAL
    0.43
     Canva
    0.43
     Digital
    0.42
     Digit
    0.42
     DL
    0.42
     RICH
    0.41
    POSITIVE LOGITS
    acción
    0.45
    ẹt
    0.44
    scissors
    0.44
    علم
    0.44
    dylib
    0.43
    ޞ
    0.43
    ajout
    0.43
    owość
    0.43
    woł
    0.43
    útbol
    0.42
    Act Density 0.016%

    No Known Activations