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

    Neuronpedia

    INDEX
    Explanations

    0 and 1 conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     থেকে
    0.39
     রেফার
    0.39
     +,
    0.36
    越大
    0.36
     или
    0.35
     इनको
    0.34
    娍
    0.34
    少ない
    0.34
     کنید
    0.34
    RAND
    0.34
    POSITIVE LOGITS
     kembali
    0.39
     dreaded
    0.39
     saludar
    0.39
     tačiau
    0.38
     samego
    0.37
     embora
    0.37
     stesso
    0.36
     notorious
    0.36
     inescap
    0.36
     wichtig
    0.36
    Act Density 0.033%

    No Known Activations