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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    On
    -0.07
    876
    -0.06
    _For
    -0.06
    >&
    -0.06
     changer
    -0.06
    _filter
    -0.06
    877
    -0.06
    _nums
    -0.06
     Pricing
    -0.06
    .For
    -0.06
    POSITIVE LOGITS
     the
    0.07
    Site
    0.07
    ська
    0.07
    .We
    0.07
    ultz
    0.07
     we
    0.07
     ${↵
    0.07
    Peer
    0.07
    olec
    0.07
    olog
    0.06
    Act Density 0.149%

    No Known Activations