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

    Neuronpedia

    INDEX
    Explanations

    kinds of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ️
    0.25
     Also
    0.24
    ina
    0.24
     मौजूद
    0.24
    boh
    0.24
    newblock
    0.23
    scaping
    0.23
    schild
    0.23
    ឈ
    0.23
    leigh
    0.23
    POSITIVE LOGITS
     sorts
    0.96
     varying
    0.54
     interest
    0.52
     sort
    0.49
     importance
    0.46
    sort
    0.45
     kinds
    0.44
     Sort
    0.43
     utmost
    0.42
    Sort
    0.41
    Act Density 0.132%

    No Known Activations