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

    Neuronpedia

    INDEX
    Explanations

    Java code related to API requests and responses

    oai_token-act-pair · gemini-2.0-flash

    request

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.82
    <bos>
    -0.78
    }))
    -0.68
    UnsafeEnabled
    -0.66
    :✨
    -0.61
    })`
    -0.60
    RegressionTest
    -0.59
     parseFrom
    -0.59
    MENAFN
    -0.59
    XmlAccessorType
    -0.58
    POSITIVE LOGITS
    uxxxx
    0.68
     WaitForSeconds
    0.60
    othesis
    0.54
    transQ
    0.54
     feit
    0.52
    jas
    0.51
    LLocation
    0.50
    asure
    0.50
    Pozdrawiam
    0.50
    stdc
    0.49
    Act Density 1.346%

    No Known Activations