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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or provision

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

    provision for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.51
    kloped
    -0.48
    antMatchers
    -0.47
     Horv
    -0.45
    InjectMocks
    -0.45
    centration
    -0.45
    HtmlAttribute
    -0.44
    unicip
    -0.43
    tiérrez
    -0.42
    ніципалі
    -0.42
    POSITIVE LOGITS
     Provision
    0.80
     provision
    0.75
    provision
    0.69
    Provision
    0.65
     Provisions
    0.64
     Provide
    0.59
     PROVISIONS
    0.59
     provisions
    0.57
     provisioning
    0.56
     nakalista
    0.52
    Act Density 0.011%

    No Known Activations