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

    Neuronpedia

    INDEX
    Explanations

    constructor arguments or code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ORDON
    0.41
    砼
    0.40
    рыма
    0.40
    ⌦
    0.39
    pv
    0.39
     Extract
    0.38
    Erro
    0.37
    MQTT
    0.37
     அதிமுக
    0.36
    Ɛ
    0.36
    POSITIVE LOGITS
     Accessibility
    0.44
    坏
    0.39
     Government
    0.39
    รี
    0.36
     CT
    0.36
    ึ้น
    0.35
     নিক
    0.35
     നിര
    0.35
     لدى
    0.35
     kracht
    0.35
    Act Density 0.000%

    No Known Activations