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

    Neuronpedia

    INDEX
    Explanations

    for applications and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    );">
    0.37
     نہيں
    0.36
    감
    0.36
    ;"
    0.35
     policeman
    0.35
     atrap
    0.33
    Madam
    0.33
    megen
    0.33
    padding
    0.33
    ualan
    0.32
    POSITIVE LOGITS
     Tiếp
    0.45
     ಯಾವ
    0.41
     ভিত্ত
    0.40
     exploit
    0.40
    StartState
    0.40
     Explo
    0.39
     Window
    0.38
    “…
    0.38
    anoj
    0.38
     Lire
    0.38
    Act Density 0.001%

    No Known Activations