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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases related to acknowledgment and affirmation in conversations

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

    Do you have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.70
     kaarangay
    -0.63
     autorytatywna
    -0.61
    majánló
    -0.60
    SequentialGroup
    -0.60
     kasarigan
    -0.59
    })*/
    -0.59
     initComponents
    -0.58
    లాలు
    -0.56
     protoimpl
    -0.55
    POSITIVE LOGITS
    ModelSerializer
    0.35
     NSCoder
    0.33
     sole
    0.32
     pon
    0.32
     ber
    0.31
    IMUM
    0.31
     rise
    0.31
     enterprise
    0.31
     just
    0.31
      
    0.31
    Act Density 0.223%

    No Known Activations