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

    Neuronpedia

    INDEX
    Explanations

    section headings and formatting in technical documents

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

    section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.91
    ंदीखरीदारी
    -0.90
     informée
    -0.89
     surla
    -0.84
    niſſe
    -0.82
     protoimpl
    -0.82
    <pad>
    -0.81
    ⟬
    -0.80
    <unused74>
    -0.80
    <unused52>
    -0.80
    POSITIVE LOGITS
     contact
    0.36
    <h4>
    0.30
    ,
    0.30
     location
    0.29
     modalités
    0.28
     rumbo
    0.28
    特
    0.27
     how
    0.27
    :
    0.27
     pocos
    0.27
    Act Density 0.008%

    No Known Activations