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

    Neuronpedia

    INDEX
    Explanations

    negative stereotypes, especially important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     radix
    0.48
     LE
    0.44
    LE
    0.43
     LEON
    0.41
    ARIES
    0.41
    ezers
    0.40
     рад
    0.40
    ERICK
    0.40
     rada
    0.38
    le
    0.38
    POSITIVE LOGITS
    idey
    0.40
    Ideally
    0.38
    hani
    0.38
    issant
    0.38
    единен
    0.37
     ideally
    0.36
    ровании
    0.36
     intimate
    0.36
    bey
    0.36
     виправи
    0.36
    Act Density 0.001%

    No Known Activations