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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conclusions and wrapping up discussions

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

    ending, concluding, finishing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pows
    -0.33
    BrowserModule
    -0.32
     armée
    -0.28
     uży
    -0.28
     hyö
    -0.27
     peran
    -0.27
     kepentingan
    -0.27
     Verkehrs
    -0.27
     mañana
    -0.26
    (
    -0.26
    POSITIVE LOGITS
     finalize
    0.76
    finalize
    0.74
     concluding
    0.74
     finish
    0.73
     closing
    0.73
     conclu
    0.72
     Closing
    0.71
     Schluß
    0.71
    enumii
    0.71
     finishing
    0.69
    Act Density 0.036%

    No Known Activations