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

    Neuronpedia

    INDEX
    Explanations

    ethics and its application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Depression
    0.40
     depression
    0.39
     catalyzed
    0.39
     freezing
    0.38
     caps
    0.38
     Bir
    0.38
     Jamb
    0.38
    看完
    0.38
     vanes
    0.38
     sadness
    0.38
    POSITIVE LOGITS
    Security
    0.40
    Durante
    0.40
    During
    0.40
    ⓪
    0.40
    Panic
    0.38
    security
    0.38
    Days
    0.38
    Digit
    0.38
    verläss
    0.38
    Pending
    0.38
    Act Density 0.002%

    No Known Activations