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

    Neuronpedia

    INDEX
    Explanations

    nuclear weapon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Developer
    0.40
     deva
    0.40
     youre
    0.38
     möjligt
    0.38
     voulez
    0.37
    maze
    0.37
     promov
    0.37
    Developers
    0.36
     developer
    0.36
    0.36
    POSITIVE LOGITS
     கிடைத்த
    0.46
     వి
    0.42
     отрима
    0.42
    razioni
    0.42
     महत्वपूर्ण
    0.41
    ProgressListener
    0.41
    賚
    0.41
    靣
    0.41
    <unused2141>
    0.41
    Theorem
    0.40
    Act Density 0.000%

    No Known Activations