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

    Neuronpedia

    INDEX
    Explanations

    questions about interest or desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yep
    0.74
    variable
    0.72
    Yep
    0.72
     podremos
    0.71
     बताऊंगा
    0.71
    rž
    0.70
     yep
    0.70
     জানে
    0.70
     competente
    0.70
     können
    0.69
    POSITIVE LOGITS
     bothers
    1.73
     excites
    1.65
     bothering
    1.65
     inspires
    1.65
     interests
    1.47
     fascin
    1.44
     feels
    1.42
     appeals
    1.40
     bother
    1.35
     inspire
    1.35
    Act Density 0.947%

    No Known Activations