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

    Neuronpedia

    INDEX
    Explanations

    technical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wellness
    -0.10
     guided
    -0.09
     威
    -0.09
     SWOT
    -0.09
     mindfulness
    -0.08
     détente
    -0.08
     wisely
    -0.08
     outdoor
    -0.08
     yok
    -0.08
    guided
    -0.08
    POSITIVE LOGITS
     때문에
    0.13
     incorrectly
    0.12
     때문
    0.11
     بسبب
    0.10
     인해
    0.10
     manchmal
    0.10
     improperly
    0.10
     prematurely
    0.10
     inadvert
    0.10
     inadvertently
    0.10
    Act Density 0.044%

    No Known Activations