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

    Neuronpedia

    INDEX
    Explanations

    words related to thinking, feelings, claims, judgements, and beliefs.

    oai_token-act-pair · gemini-2.0-flash

    expressing belief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TIMESTAMP
    -0.51
    ̍
    -0.50
     ujednoznacz
    -0.49
     evidentemente
    -0.47
     crees
    -0.47
    <bos>
    -0.47
    ria
    -0.45
    cher
    -0.44
    Ges
    -0.44
     Crank
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.92
    StoryboardSegue
    0.91
     resourceCulture
    0.80
     BrowserModule
    0.79
     estekak
    0.77
    CppCodeGen
    0.70
    WebElementEntity
    0.70
    HasForeignKey
    0.69
     onPostExecute
    0.69
    RepeatedField
    0.68
    Act Density 6.995%

    No Known Activations