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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions indicating understanding or acknowledgment in conversation

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

    you know and like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reprodução
    -0.32
    ərbaycan
    -0.32
    autant
    -0.30
     transférez
    -0.29
     ideias
    -0.29
     tanta
    -0.28
     doigt
    -0.28
     ſol
    -0.28
     gelang
    -0.26
     préférence
    -0.26
    POSITIVE LOGITS
     CreateTagHelper
    0.70
     المعيارى
    0.66
    ItemBackground
    0.61
    PerformLayout
    0.59
    urlencoded
    0.56
     AppCompat
    0.53
     <<<<<<<<<<<<<<
    0.52
    كويكب
    0.52
    GHIJKLM
    0.52
    addGap
    0.51
    Act Density 0.016%

    No Known Activations