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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or probability regarding behaviors or outcomes

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

    likely to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.68
    şört
    -0.55
    riculum
    -0.54
    SBATCH
    -0.52
    SourceChecksum
    -0.51
     Verſ
    -0.51
     Monfieur
    -0.51
    akaian
    -0.51
     ligiloj
    -0.49
     disfru
    -0.48
    POSITIVE LOGITS
     tendency
    0.43
    ">//
    0.39
    gridx
    0.34
    day
    0.33
    east
    0.32
     chance
    0.32
    }());
    0.32
     public
    0.31
    sion
    0.31
    ender
    0.31
    Act Density 0.163%

    No Known Activations