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

    Neuronpedia

    INDEX
    Explanations

    these topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     появление
    0.34
     paragraph
    0.33
     విషయం
    0.32
     作为
    0.31
     কথাটা
    0.31
     gonflement
    0.31
    手術
    0.31
    ubation
    0.31
     डिजाईन
    0.30
     accusation
    0.30
    POSITIVE LOGITS
    ườ
    0.32
    там
    0.31
    ਿ
    0.31
    że
    0.30
    их
    0.29
     inadequ
    0.29
    િ
    0.29
    ت
    0.28
     impedances
    0.28
    ત્
    0.28
    Act Density 0.075%

    No Known Activations