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

    Neuronpedia

    INDEX
    Explanations

    terms related to reinforcement learning and its methodologies

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

    reinforcement learning concepts and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.44
     initComponents
    -0.41
    ="@+
    -0.41
     Picchu
    -0.39
    jerg
    -0.38
     nonUne
    -0.38
    Near
    -0.38
     SearchView
    -0.37
    énario
    -0.37
    tragen
    -0.37
    POSITIVE LOGITS
    DIPSETTING
    0.51
    envs
    0.51
    WireFormatLite
    0.49
    DataPropertyName
    0.44
     gym
    0.43
     reinforcement
    0.42
    forcement
    0.42
    もしれません
    0.41
     pinulongan
    0.41
     ProtoMessage
    0.40
    Act Density 0.053%

    No Known Activations