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

    Neuronpedia

    INDEX
    Explanations

    lemon combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.45
     GEL
    0.40
    t
    0.40
    isnan
    0.40
    sembl
    0.39
    तरा
    0.39
     mediados
    0.38
    c
    0.38
    MaxValue
    0.37
    传来
    0.37
    POSITIVE LOGITS
    Lem
    0.45
    檬
    0.45
     হলুদ
    0.44
    র্য
    0.44
     lem
    0.43
    Redirect
    0.41
     Lem
    0.39
     বাতাস
    0.39
     lemma
    0.39
     inex
    0.39
    Act Density 0.003%

    No Known Activations