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

    Neuronpedia

    INDEX
    Explanations

    escaping controlling relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waveguide
    0.48
    னாக
    0.47
     compounds
    0.47
     attenuate
    0.47
    énés
    0.46
     mutually
    0.45
     संयोजन
    0.44
     permissive
    0.44
    il
    0.44
     interacción
    0.44
    POSITIVE LOGITS
     Afternoon
    0.47
    Loy
    0.46
     Loyalty
    0.45
    QU
    0.44
    بدا
    0.44
    FF
    0.44
    pound
    0.42
    Por
    0.42
    Massachusetts
    0.42
    按摩
    0.42
    Act Density 0.002%

    No Known Activations