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

    Neuronpedia

    INDEX
    Explanations

    anorectic, eating disorder, engines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łu
    0.48
    reversed
    0.46
    ொருள்
    0.45
    apabb
    0.45
    μένων
    0.45
    amentos
    0.45
    ap
    0.44
    o
    0.44
    a
    0.44
    ഷ്ട്ര
    0.43
    POSITIVE LOGITS
     contribute
    0.49
     Alhamdulillah
    0.47
     carry
    0.46
     carries
    0.45
     carried
    0.44
     Contribute
    0.44
     day
    0.44
     подробно
    0.44
     generation
    0.43
     contribu
    0.43
    Act Density 0.025%

    No Known Activations