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

    Neuronpedia

    INDEX
    Explanations

    listing, prepare, sizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    晖
    0.41
    踟
    0.39
     ऑफिसर
    0.39
    Ո
    0.38
    倝
    0.37
     solucion
    0.37
    ário
    0.36
     Lindsay
    0.36
     फेमस
    0.36
    張り
    0.36
    POSITIVE LOGITS
     mores
    0.39
     চুক্ত
    0.39
    IC
    0.38
     pang
    0.38
    ICAN
    0.38
     variability
    0.37
     भेदभाव
    0.36
    िव
    0.35
    ERN
    0.35
    ុន
    0.35
    Act Density 0.001%

    No Known Activations