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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     την
    0.96
     Suppose
    0.92
     sparsity
    0.90
    ()=>{
    0.90
     대부분
    0.89
     perfusion
    0.89
     indetermin
    0.88
     dalších
    0.88
    可以
    0.87
     macam
    0.86
    POSITIVE LOGITS
    en
    1.05
    ar
    1.04
    ac
    0.92
    od
    0.90
    ta
    0.90
    ab
    0.89
    ap
    0.89
    a
    0.89
    id
    0.87
    an
    0.84
    Act Density 0.172%

    No Known Activations