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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusivity and restricted access

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

    private exclusive access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    forRoot
    -0.30
     становника
    -0.28
    DllImport
    -0.28
    杯
    -0.28
     beliau
    -0.26
     Dr
    -0.26
     înc
    -0.25
    锆
    -0.25
    __).
    -0.25
    Karriere
    -0.24
    POSITIVE LOGITS
     confidential
    0.74
     Confidential
    0.72
    tagHelperRunner
    0.72
     &___
    0.69
    IDENTIAL
    0.68
     PRIVATE
    0.68
     private
    0.66
     secret
    0.65
     SECRET
    0.63
    Confidential
    0.63
    Act Density 0.067%

    No Known Activations