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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating necessity or obligation

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

    they + modal verb + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lèvres
    -0.46
    ChildScrollView
    -0.46
     imageName
    -0.43
    PickerController
    -0.43
    سطس
    -0.42
     enfans
    -0.42
    aarrggbb
    -0.42
    IntoConstraints
    -0.41
     resourceCulture
    -0.41
    CodedInputStream
    -0.41
    POSITIVE LOGITS
    they
    0.92
     They
    0.87
    They
    0.85
     Mereka
    0.84
     mereka
    0.84
     they
    0.83
    Mereka
    0.82
    their
    0.78
    Them
    0.78
    them
    0.77
    Act Density 0.061%

    No Known Activations