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

    Neuronpedia

    INDEX
    Explanations

    recipe preparation steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plufieurs
    0.49
    SelfPermission
    0.48
    运算符
    0.46
     objRequest
    0.46
    FBSDKGraph
    0.46
    进而
    0.46
    getParameters
    0.45
     axioms
    0.45
     equivariant
    0.45
     multivalued
    0.45
    POSITIVE LOGITS
     stir
    1.11
     Stir
    1.03
     gently
    1.00
     drizzle
    1.00
     stirring
    0.97
     lightly
    0.96
     sprinkle
    0.96
    stir
    0.96
     Gently
    0.94
     stirred
    0.92
    Act Density 0.107%

    No Known Activations