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

    Neuronpedia

    INDEX
    Explanations

    Detected gas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mr
    0.42
    Bn
    0.41
    Fmat
    0.40
    inn
    0.40
    Herald
    0.39
    heim
    0.39
    Bm
    0.39
    🏻
    0.39
     rubric
    0.39
    Gul
    0.39
    POSITIVE LOGITS
     Stack
    0.43
    就把
    0.37
    涜
    0.37
     chơi
    0.37
     চরিত
    0.36
     Capsule
    0.35
     Cine
    0.35
     Audio
    0.35
    ([(
    0.35
    itabbo
    0.35
    Act Density 0.000%

    No Known Activations