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

    Neuronpedia

    INDEX
    Explanations

    Hall ways Taking izes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    टन
    0.45
    сель
    0.43
    \/}
    0.43
     және
    0.42
    เสนอ
    0.42
    즈
    0.42
     FODC
    0.40
    ynomial
    0.40
    すなわち
    0.40
    稩
    0.40
    POSITIVE LOGITS
     h
    0.55
     m
    0.51
     P
    0.49
     g
    0.49
     y
    0.47
     iron
    0.47
    je
    0.46
     tractors
    0.45
     errors
    0.45
     l
    0.44
    Act Density 0.003%

    No Known Activations