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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "dois" and variations of the verb "to do."

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

    have to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.59
     objet
    -0.38
    Bioaccumulative
    -0.37
    mbitos
    -0.36
     tumba
    -0.35
    SetBool
    -0.35
     kaarangay
    -0.35
    kungan
    -0.35
     onOptions
    -0.34
     unlimited
    -0.34
    POSITIVE LOGITS
     must
    1.18
     Must
    1.12
    must
    1.11
    Must
    1.11
     harus
    1.05
     MUST
    1.00
     phải
    0.98
     moeten
    0.95
     باید
    0.91
    ต้อง
    0.91
    Act Density 0.108%

    No Known Activations