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

    Neuronpedia

    INDEX
    Explanations

    future-oriented statements or actions related to processes and approvals

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

    completed actions after "be"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puedas
    -0.33
     quieras
    -0.31
     sjø
    -0.31
     esfuer
    -0.31
    又能
    -0.29
     dễ
    -0.28
     parezca
    -0.28
     ultimate
    -0.27
    ultimate
    -0.27
    Ultimate
    -0.26
    POSITIVE LOGITS
     myſelf
    0.82
     betweenstory
    0.82
    oneofs
    0.73
    msgTypes
    0.70
    ſicht
    0.70
     stiefe
    0.68
    ſchaft
    0.68
    AddHtmlAttribute
    0.68
    principalColumn
    0.68
     Geiſt
    0.68
    Act Density 0.052%

    No Known Activations