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

    Neuronpedia

    INDEX
    Explanations

    lists and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oko
    0.50
     hỗ
    0.49
     kwal
    0.46
     rechts
    0.45
     ila
    0.44
    ål
    0.44
    setTo
    0.43
     inger
    0.42
     från
    0.42
     rond
    0.42
    POSITIVE LOGITS
    tissue
    0.60
     GRA
    0.51
    ステム
    0.49
    ATED
    0.48
    norms
    0.48
    しています
    0.48
    »;
    0.48
    LEMENT
    0.47
    pessoas
    0.46
     LINE
    0.46
    Act Density 0.002%

    No Known Activations