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

    Neuronpedia

    INDEX
    Explanations

    total movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     노력
    0.69
    INPUT
    0.67
    ränkt
    0.67
     versuchen
    0.67
    ukunft
    0.66
     geared
    0.65
     destinée
    0.65
    Inputs
    0.64
    psons
    0.64
    convén
    0.64
    POSITIVE LOGITS
     found
    4.06
     observed
    3.94
     discovered
    3.62
     detected
    3.48
    found
    3.39
     Found
    3.33
    observed
    3.18
     ditemukan
    3.12
    Found
    3.10
     gefunden
    3.08
    Act Density 1.104%

    No Known Activations