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

    Neuronpedia

    INDEX
    Explanations

    negative connotations or terms associated with disappointment

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

    forms and input fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.70
    InjectMocks
    -0.67
    parsedMessage
    -0.66
    AddTagHelper
    -0.66
    ReferenceEquals
    -0.62
    onAttach
    -0.61
    DebuggerNonUser
    -0.60
    atlas
    -0.59
    CPtr
    -0.58
    expandindo
    -0.58
    POSITIVE LOGITS
     Form
    0.81
     form
    0.75
    Form
    0.68
     Forms
    0.63
    form
    0.60
     forms
    0.60
    FormTagHelper
    0.60
     forme
    0.59
     FORM
    0.57
    Forms
    0.55
    Act Density 0.002%

    No Known Activations