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

    Neuronpedia

    INDEX
    Explanations

    specific attributes and aspects related to relationships and outcomes

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

    specifies quantity or duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ativement
    -0.37
    principalTable
    -0.37
    ACHUSET
    -0.37
     paramInt
    -0.35
    Reprodução
    -0.35
    ELEMENTS
    -0.35
     cauſe
    -0.35
    package
    -0.34
     Inſ
    -0.34
     whoſe
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.65
     surla
    0.60
     snoring
    0.53
    StoryboardSegue
    0.52
    ſicht
    0.52
     esternos
    0.52
    0.50
    0.50
    ſelben
    0.50
    Dislikes
    0.50
    Act Density 0.030%

    No Known Activations