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

    Neuronpedia

    INDEX
    Explanations

    markt en motorrijwielen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    appell
    0.44
     invo
    0.41
     Akt
    0.39
     établissement
    0.39
     Kla
    0.39
     IDEA
    0.38
     Nr
    0.37
     constaté
    0.37
    ступает
    0.37
     geheel
    0.37
    POSITIVE LOGITS
     nifty
    0.43
     tabb
    0.43
     misconceptions
    0.41
    גע
    0.40
    cciona
    0.40
     shackles
    0.39
     rankings
    0.39
    OnError
    0.39
     confuses
    0.39
    することで
    0.38
    Act Density 0.002%

    No Known Activations