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

    Neuronpedia

    INDEX
    Explanations

    elements related to code and program structure

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

    public function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.76
    Hochspringen
    -0.57
     defaultstate
    -0.55
    aarrggbb
    -0.54
     lenker
    -0.53
    ondissement
    -0.52
     Italijanski
    -0.50
     esternos
    -0.49
     nonUne
    -0.49
    HasAnnotation
    -0.48
    POSITIVE LOGITS
     pouvoit
    0.50
     étoient
    0.40
     dépend
    0.37
    ToInt
    0.36
     auroit
    0.36
     étoit
    0.34
    OrUpdate
    0.34
     avoient
    0.33
     additions
    0.32
    FAQ
    0.32
    Act Density 0.002%

    No Known Activations