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

    Neuronpedia

    INDEX
    Explanations

    manner of action

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veya
    0.93
    如果您
    0.83
     dvs
    0.82
     hoặc
    0.79
     또는
    0.78
    例如
    0.76
     insbesondere
    0.75
    如果在
    0.75
     tzv
    0.75
     &/
    0.74
    POSITIVE LOGITS
     nervously
    0.98
    再び
    0.83
     beside
    0.82
     awkwardly
    0.81
     вновь
    0.80
     clums
    0.79
     momentarily
    0.78
     again
    0.77
    .“
    0.77
     furiously
    0.77
    Act Density 0.202%

    No Known Activations