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

    Neuronpedia

    INDEX
    Explanations

    OpenAPI specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     updateTotal
    0.43
     Rfe
    0.43
     essentiellement
    0.42
     "("
    0.42
     चिक
    0.41
    指示
    0.41
    <unused63>
    0.40
    setHorizontal
    0.39
     FXMLLoader
    0.39
     Rfc
    0.39
    POSITIVE LOGITS
    itsyn
    0.39
    CL
    0.38
     בי
    0.37
    abi
    0.37
     корот
    0.37
    они
    0.35
    ugen
    0.34
    uro
    0.34
     accidents
    0.34
     иных
    0.34
    Act Density 0.000%

    No Known Activations