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

    Neuronpedia

    INDEX
    Explanations

    caution and conditional warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firebase
    0.42
     width
    0.40
     shootings
    0.40
     lidt
    0.40
     tabBar
    0.40
     statusBar
    0.40
     biología
    0.39
     shooting
    0.39
     âng
    0.38
     variabile
    0.38
    POSITIVE LOGITS
     carefully
    0.79
     Carefully
    0.76
     risky
    0.75
     ONLY
    0.73
    风险
    0.73
     riesgo
    0.73
     caution
    0.72
    慎
    0.71
     risiko
    0.70
     cautioned
    0.69
    Act Density 0.276%

    No Known Activations