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

    Neuronpedia

    INDEX
    Explanations

    still shorter or complete poem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     partitions
    0.48
    Converter
    0.44
     azy
    0.43
     ejected
    0.42
     entfernen
    0.42
     signes
    0.42
     σα
    0.41
     والن
    0.40
     вто
    0.40
     exchanger
    0.40
    POSITIVE LOGITS
    oises
    0.47
    ihe
    0.46
    िंग्स
    0.42
     menambah
    0.42
     îmb
    0.42
    i
    0.42
    붐
    0.42
    ｉ
    0.41
     riječ
    0.41
    กฏ
    0.40
    Act Density 0.001%

    No Known Activations