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

    Neuronpedia

    INDEX
    Explanations

    cause severe injury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extend
    0.45
    bentuk
    0.43
    target
    0.43
    element
    0.40
     unamb
    0.40
    ['
    0.38
     моего
    0.38
    bbero
    0.38
     watchdog
    0.38
    arei
    0.38
    POSITIVE LOGITS
     LOUIS
    0.43
     ServiceNow
    0.43
     Huskies
    0.42
     Philippe
    0.41
    卽
    0.41
    辇
    0.40
    Homme
    0.39
     کہنے
    0.38
    ති
    0.38
     Hockey
    0.38
    Act Density 0.001%

    No Known Activations