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

    Neuronpedia

    INDEX
    Explanations

    handling, consuming, processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ach
    0.42
     prefque
    0.38
     भेजना
    0.37
     छोड़
    0.37
     lapses
    0.36
    放在
    0.36
    entro
    0.36
     fehlen
    0.36
     Ach
    0.35
    Renewal
    0.35
    POSITIVE LOGITS
     consume
    0.94
     consuming
    0.92
     consumes
    0.88
     processing
    0.87
     utilize
    0.86
     utilization
    0.84
     accept
    0.82
     accepting
    0.81
     обрабо
    0.81
     Verarbeitung
    0.80
    Act Density 0.084%

    No Known Activations