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

    Neuronpedia

    INDEX
    Explanations

    types, specific types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    azolin
    0.76
    ැල
    0.67
    urnama
    0.62
    ನಿ
    0.61
    xcuserdata
    0.61
    <unused474>
    0.60
    PastPositions
    0.60
    幾個
    0.59
     raggiunto
    0.59
     délais
    0.59
    POSITIVE LOGITS
     type
    6.10
     types
    5.67
    type
    5.36
     tipo
    5.31
     Type
    5.16
    类型
    4.98
    Type
    4.96
     Types
    4.85
    types
    4.81
     TYPE
    4.63
    Act Density 1.707%

    No Known Activations