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

    Neuronpedia

    INDEX
    Explanations

    code or descriptive text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ance
    0.46
     وتح
    0.45
    less
    0.45
     stessa
    0.44
    ة
    0.44
    和
    0.44
    ia
    0.44
    প্রায়
    0.44
    并在
    0.43
    ラ
    0.43
    POSITIVE LOGITS
    OHAMA
    0.48
     olefin
    0.45
    лятор
    0.43
     escrib
    0.42
     obey
    0.41
     reasonableness
    0.41
     იყოს
    0.40
     violation
    0.40
     ausführ
    0.40
     operator
    0.40
    Act Density 0.000%

    No Known Activations