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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to customer service interactions and dining establishments

    oai_token-act-pair · gemini-2.0-flash

    customer service people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зулта
    -0.70
     bezeichneter
    -0.69
     ModelExpression
    -0.68
    TargetException
    -0.68
    ništvo
    -0.66
     podjela
    -0.65
     nakalista
    -0.65
    UnknownFields
    -0.65
    providedIn
    -0.65
    setVerticalGroup
    -0.63
    POSITIVE LOGITS
    <bos>
    0.80
    馃
    0.41
     sobrevivir
    0.41
     onAnimation
    0.38
    ंदीखरीदारी
    0.37
    +#+#
    0.37
    ttino
    0.37
     tumba
    0.36
    stood
    0.35
     внимание
    0.35
    Act Density 0.770%

    No Known Activations