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

    Neuronpedia

    INDEX
    Explanations

    treating these fires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snatched
    0.48
    Localization
    0.45
     monument
    0.44
    윽
    0.43
    localize
    0.43
     Gestaltung
    0.42
    터를
    0.41
     şark
    0.41
     ලද
    0.41
     snatch
    0.40
    POSITIVE LOGITS
     amp
    0.48
    <0xB5>
    0.43
    INO
    0.43
     Amp
    0.43
     উদাহরণ
    0.42
    ino
    0.42
     ino
    0.42
    <
    0.41
    <0xBA>
    0.41
    гти
    0.41
    Act Density 0.000%

    No Known Activations