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

    Neuronpedia

    INDEX
    Explanations

    on a / on the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    phosphorylation
    0.47
    classAttribute
    0.45
    bagai
    0.44
    chemical
    0.44
    asas
    0.41
    esistenza
    0.41
    CHEMICAL
    0.41
    耖
    0.41
    adrenergic
    0.41
    }{
    0.41
    POSITIVE LOGITS
     vehicles
    0.49
     véhicules
    0.48
     розы
    0.46
     mà
    0.46
     vehículos
    0.44
    车辆
    0.44
     DHCP
    0.41
     新作
    0.41
     hybrids
    0.40
     SOME
    0.39
    Act Density 0.017%

    No Known Activations