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

    Neuronpedia

    INDEX
    Explanations

    potential outcomes and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Performs
    0.30
     Wants
    0.29
     skrev
    0.29
     chooses
    0.29
     Maintains
    0.29
     undertakes
    0.28
     hears
    0.28
     conocen
    0.27
     thinks
    0.27
     perceives
    0.27
    POSITIVE LOGITS
     necessitate
    0.56
     occur
    0.51
     result
    0.50
     correspond
    0.47
     resemble
    0.47
     contain
    0.47
     serve
    0.46
     coincide
    0.46
     encompass
    0.46
     constitute
    0.46
    Act Density 0.466%

    No Known Activations