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

    Neuronpedia

    INDEX
    Explanations

    Gemma project links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pod
    0.83
    Под
    0.77
     فیصلہ
    0.76
    Run
    0.74
    Pod
    0.73
    फोर
    0.70
     screenplay
    0.69
     Run
    0.69
    Legend
    0.68
     multiuser
    0.68
    POSITIVE LOGITS
     Thames
    0.75
     Responsible
    0.71
     cricketers
    0.69
     tossed
    0.69
     ratepayers
    0.68
    thorn
    0.68
     jetty
    0.68
     Tho
    0.67
     Stores
    0.66
    gem
    0.65
    Act Density 0.055%

    No Known Activations