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

    Neuronpedia

    INDEX
    Explanations

    words related to actions and processes

    oai_token-act-pair · gemini-2.0-flash

    flow/movement of materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    protoc
    -0.54
     '+':
    -0.52
     chi̍t
    -0.52
    classnames
    -0.50
    GRANTED
    -0.49
     Superhost
    -0.48
    borgs
    -0.47
    cryption
    -0.47
    inheritdoc
    -0.47
     Peninsula
    -0.47
    POSITIVE LOGITS
    <bos>
    0.76
    Manbalar
    0.61
    saraba
    0.60
     destinés
    0.55
     destinées
    0.54
    appendTo
    0.54
    INCREF
    0.51
     gratuits
    0.49
     destinations
    0.49
    Output
    0.48
    Act Density 2.538%

    No Known Activations