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

    Neuronpedia

    INDEX
    Explanations

    sentences beginning or containing "there" or "it" plus another pronoun

    oai_token-act-pair · gemini-2.0-flash

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.71
     onAnimation
    -0.66
    ftagPool
    -0.65
    +#+#
    -0.62
     itſelf
    -0.60
    enumii
    -0.59
    LookAnd
    -0.58
     nemlig
    -0.57
     Cæsar
    -0.57
    OGND
    -0.57
    POSITIVE LOGITS
    BeginContext
    0.51
     Open
    0.46
     open
    0.46
     comes
    0.45
     пун
    0.44
    opens
    0.44
    ốt
    0.43
    Demografie
    0.43
    open
    0.43
    comes
    0.43
    Act Density 0.153%

    No Known Activations