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

    Neuronpedia

    INDEX
    Explanations

    runners-up and mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.84
     El
    0.77
     A
    0.74
     Ai
    0.70
     AL
    0.68
     U
    0.66
     Q
    0.66
     this
    0.64
     Er
    0.64
     R
    0.63
    POSITIVE LOGITS
    aar
    0.70
    ៥
    0.64
    ap
    0.61
    indoor
    0.61
    endlich
    0.61
    vaegir
    0.60
    aarr
    0.59
    ٹر
    0.59
    lcnaf
    0.59
    kind
    0.59
    Act Density 0.001%

    No Known Activations