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

    Neuronpedia

    INDEX
    Explanations

    focus:ring-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forem
    0.51
    कान
    0.48
     homebuyers
    0.47
    lap
    0.46
     propriety
    0.46
    pres
    0.44
     kasut
    0.44
     memakai
    0.44
    July
    0.44
     commemor
    0.44
    POSITIVE LOGITS
     サイ
    0.60
    Ң
    0.59
     codons
    0.56
     り
    0.55
     塩
    0.54
    ITION
    0.54
     инфек
    0.54
     ры
    0.52
     moistur
    0.52
     ကျွန်
    0.52
    Act Density 0.000%

    No Known Activations