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

    Neuronpedia

    INDEX
    Explanations

    urgency, awareness, resilience, communicating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.58
    indent
    0.51
    ma
    0.49
     ADMIN
    0.48
    К
    0.48
    user
    0.46
    orsky
    0.46
    ctx
    0.45
    ardin
    0.45
    eta
    0.44
    POSITIVE LOGITS
     banheiro
    0.56
     సామ
    0.45
     prowad
    0.41
     îmb
    0.41
     తయారు
    0.41
     prohib
    0.41
     były
    0.41
    ുപത്രി
    0.40
    iyaç
    0.40
     бола
    0.40
    Act Density 0.002%

    No Known Activations