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

    Neuronpedia

    INDEX
    Explanations

    circuits and faults

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ausgezeichnet
    -0.08
     bos
    -0.07
     hormon
    -0.07
     mastering
    -0.07
    .annotations
    -0.07
     \↵
    -0.07
    .educ
    -0.07
    _caption
    -0.07
    либ
    -0.07
     DONE
    -0.07
    POSITIVE LOGITS
     ആക്രമ
    0.10
     outage
    0.10
     दुर्घ
    0.09
    事故
    0.09
     Attack
    0.09
     catastrophic
    0.09
     potência
    0.08
     авар
    0.08
     escalation
    0.08
     Unfall
    0.08
    Act Density 0.004%

    No Known Activations