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

    Neuronpedia

    INDEX
    Explanations

    programming functions and variables related to encoding and validation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    variable names like b and m

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.48
    postsleuth
    -0.39
    deviantart
    -0.37
    <bos>
    -0.36
     AssemblyProduct
    -0.35
    mogorov
    -0.34
    hoeddwyd
    -0.33
     transacciones
    -0.33
     Italij
    -0.32
     apsau
    -0.32
    POSITIVE LOGITS
     חיצוניים
    0.59
    stateProvider
    0.54
    ViewFeatures
    0.53
    SharedDtor
    0.53
     invokingState
    0.52
    IntoConstraints
    0.51
     المعيارى
    0.48
    parsedMessage
    0.48
     _)
    0.48
     jedis
    0.46
    Act Density 0.020%

    No Known Activations