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

    Neuronpedia

    INDEX
    Explanations

    phrases and ideas related to the impact of beliefs and choices on future outcomes

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

    Questions or statements ending in question marks

    np_acts-logits-general · gemini-2.0-flash

    questions ending in question marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lateinit
    -0.67
     nemlig
    -0.66
    UseVisualStyle
    -0.61
     einiges
    -0.57
    ImageContext
    -0.56
     bezeichneter
    -0.56
    .。
    -0.56
    følgelig
    -0.56
     MessageBoxIcon
    -0.55
    .";
    -0.54
    POSITIVE LOGITS
    ?
    2.47
    ?”
    2.25
    ?
    2.23
    ?"
    2.15
    ?)
    2.08
    ?}
    2.07
    ؟
    2.05
    ?</
    1.96
    ?'
    1.92
    %?
    1.91
    Act Density 1.010%

    No Known Activations