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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to cooperation and openness

    oai_token-act-pair · gemini-2.0-flash

    Sharing or repeating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.51
    kloped
    -0.51
    gend
    -0.50
    irms
    -0.48
     Montenegro
    -0.46
     Flip
    -0.46
     flip
    -0.46
     just
    -0.45
    RegressionTest
    -0.44
    vaadin
    -0.43
    POSITIVE LOGITS
     تانيه
    0.71
     مشين
    0.68
    Hochspringen
    0.68
     springfox
    0.67
    ChildScrollView
    0.67
     Normdatei
    0.66
     Unidas
    0.65
     Welles
    0.64
     AppCompatTheme
    0.64
     Anson
    0.64
    Act Density 1.536%

    No Known Activations