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

    Neuronpedia

    INDEX
    Explanations

    trade speed for torque

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toNumber
    0.42
     到
    0.38
     ******
    0.38
     tới
    0.37
     setToDefault
    0.37
    jskim
    0.36
     দৃ
    0.36
     menuju
    0.36
     To
    0.35
     vast
    0.35
    POSITIVE LOGITS
    /\
    0.55
    /$
    0.52
    for
    0.50
    換
    0.49
    换
    0.46
    裏
    0.44
    /#{
    0.41
    :=\
    0.40
    /?
    0.40
    эх
    0.38
    Act Density 0.004%

    No Known Activations