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

    Neuronpedia

    INDEX
    Explanations

    constantly changing or evolving concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mechanism
    0.71
     pobre
    0.64
     mecanismos
    0.64
     Legend
    0.63
     पोखर
    0.63
     pitiful
    0.63
     mecanismo
    0.62
    سباب
    0.62
     défaut
    0.61
     Mechanism
    0.61
    POSITIVE LOGITS
     changing
    2.58
    changing
    2.32
     Changing
    2.23
    Changing
    2.21
     evolving
    2.07
     shifting
    1.96
     changed
    1.94
    变化
    1.88
     변화
    1.88
    変化
    1.84
    Act Density 1.142%

    No Known Activations