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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a comparison

    oai_token-act-pair · gemini-2.0-flash

    similarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.74
     AttributeSet
    -0.67
    \{\\
    -0.65
     ivelany
    -0.65
     Мексичка
    -0.62
    الحياه
    -0.61
     comparación
    -0.58
    awtextra
    -0.57
     fieldNum
    -0.56
     dAtA
    -0.56
    POSITIVE LOGITS
     soweit
    0.54
     emb
    0.49
    lah
    0.47
    
    0.47
     paper
    0.47
    fills
    0.46
     直
    0.46
     Obrador
    0.45
    onica
    0.45
    UnitTesting
    0.45
    Act Density 1.071%

    No Known Activations