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

    Neuronpedia

    INDEX
    Explanations

    reporting structure, trust, AI, combined, LED

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Failure
    0.52
     Incoming
    0.47
     severance
    0.46
     Fibre
    0.46
     Laser
    0.46
     Healthy
    0.45
     consideration
    0.44
     subterr
    0.43
     laser
    0.43
     discharging
    0.43
    POSITIVE LOGITS
    tFileInputExcel
    0.49
    Anda
    0.47
    ów
    0.46
     çek
    0.46
     wyświet
    0.46
     იყო
    0.45
    敚
    0.45
     එහි
    0.45
    omètre
    0.44
     отмети
    0.44
    Act Density 0.000%

    No Known Activations