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

    Neuronpedia

    INDEX
    Explanations

    technical components and devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opleiding
    0.71
     völl
    0.60
     Autón
    0.59
    prakt
    0.58
    írez
    0.58
    aholic
    0.58
    Exponent
    0.58
     Fragmentation
    0.58
     행복
    0.57
     anek
    0.57
    POSITIVE LOGITS
     moving
    0.74
     rotating
    0.66
     electrodes
    0.65
     mirrors
    0.64
     movable
    0.61
     flexible
    0.58
     conductors
    0.56
     moveable
    0.55
     collectors
    0.55
    rotating
    0.55
    Act Density 0.322%

    No Known Activations