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

    Neuronpedia

    INDEX
    Explanations

    prevent from or avoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izieren
    0.15
     Geme
    0.15
     اکثر
    0.15
    نيك
    0.14
    Meas
    0.14
     willful
    0.14
    Google
    0.14
     پزش
    0.14
     hacerse
    0.14
    enderal
    0.14
    POSITIVE LOGITS
     foot
    0.14
    foot
    0.14
    receptor
    0.14
     чув
    0.13
     osnov
    0.13
     imbalances
    0.13
     FOOT
    0.12
     জাক
    0.12
    istered
    0.12
    ības
    0.12
    Act Density 0.034%

    No Known Activations