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

    Neuronpedia

    INDEX
    Explanations

    pieces of code or data structures related to configurations and parameters

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

    hexadecimal key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.55
     informée
    -0.54
     betweenstory
    -0.50
    utives
    -0.50
     noDo
    -0.49
    InjectAttribute
    -0.47
     cherchés
    -0.46
     besti
    -0.44
    ſelves
    -0.44
    FormTagHelper
    -0.44
    POSITIVE LOGITS
    styleUrls
    0.44
     виправивши
    0.43
    WithMany
    0.43
     orejas
    0.42
     própria
    0.41
    mapStateToProps
    0.41
    fjspx
    0.41
    只好
    0.40
     meestal
    0.40
    });*/
    0.39
    Act Density 0.097%

    No Known Activations