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

    Neuronpedia

    INDEX
    Explanations

    words indicating a decrease in magnitude or amount

    oai_token-act-pair · gemini-2.0-flash

    decline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     declined
    -1.67
     decline
    -1.65
     declines
    -1.52
     declining
    -1.47
     refused
    -1.36
     refuse
    -1.30
     Decline
    -1.29
    decline
    -1.27
     refusal
    -1.27
    Decline
    -1.26
    POSITIVE LOGITS
    +#+
    0.57
     بيها
    0.55
    ordeel
    0.51
     CreateTagHelper
    0.50
     ExecuteAsync
    0.48
    yakarta
    0.48
    Unmanaged
    0.47
    tiller
    0.47
     doInBackground
    0.47
    Jersey
    0.47
    Act Density 6.863%

    No Known Activations