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

    Neuronpedia

    INDEX
    Explanations

    consequential

    np_max-act · gemini-2.0-flash

    The neuron activates on the “indirect or consequential” damages clause in legal/license disclaimers, especially detecting the word “consequential.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    RowAnimation
    -0.06
    퇴
    -0.06
     ')[
    -0.06
    '))->
    -0.06
    /Open
    -0.06
    FontSize
    -0.06
     ziy
    -0.06
    izando
    -0.06
    AccessToken
    -0.05
    ])*
    -0.05
    POSITIVE LOGITS
     consequential
    0.08
     thunder
    0.07
     numerous
    0.06
     Classified
    0.06
     CONSEQUENTIAL
    0.06
     successor
    0.06
    =G
    0.06
    终于
    0.06
    itionally
    0.06
     Clem
    0.06
    Act Density 0.001%

    No Known Activations