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

    Neuronpedia

    INDEX
    Explanations

    control or pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aset
    0.40
     Mendel
    0.39
     Pip
    0.38
     Lay
    0.38
     hon
    0.37
    sey
    0.37
     SIA
    0.37
     blew
    0.36
     Strike
    0.36
    selectedIndex
    0.36
    POSITIVE LOGITS
    控制
    0.46
     контроля
    0.45
    CONTROL
    0.43
    control
    0.42
     controlling
    0.42
    kontrol
    0.42
    Pressure
    0.41
    principles
    0.40
    pressure
    0.39
    controlling
    0.39
    Act Density 0.076%

    No Known Activations