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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਉਸ
    0.53
    ler
    0.49
    iler
    0.48
    ie
    0.47
    gger
    0.47
    𝐫
    0.47
    গির
    0.46
    kräft
    0.46
    骡
    0.46
    il
    0.45
    POSITIVE LOGITS
    0.56
     ID
    0.50
     around
    0.49
     schemes
    0.45
     CD
    0.44
     IB
    0.44
     ,"
    0.44
     antiga
    0.44
     bact
    0.43
     LIB
    0.43
    Act Density 0.000%

    No Known Activations