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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating improvement or the need for enhancement in various contexts

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

    better integration, systematic analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.42
    ValueStyle
    -0.36
     surla
    -0.35
    enterOuterAlt
    -0.34
    CodedInputStream
    -0.32
     aufzu
    -0.32
    weile
    -0.31
    Circle
    -0.31
    UseVisualStyle
    -0.30
     eût
    -0.30
    POSITIVE LOGITS
    ftance
    0.70
    chließend
    0.59
     leaſt
    0.56
    ſtance
    0.54
     Majefty
    0.53
    fjspx
    0.52
     reaſon
    0.52
    Diweddarwch
    0.52
     ממש
    0.51
     politics
    0.50
    Act Density 0.043%

    No Known Activations