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

    Neuronpedia

    INDEX
    Explanations

    effective immediately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _IV
    -0.07
     Gron
    -0.07
    _socket
    -0.06
    धर
    -0.06
     lids
    -0.06
    BuildContext
    -0.06
    ))/
    -0.06
    /feed
    -0.06
    174
    -0.06
    Spoiler
    -0.06
    POSITIVE LOGITS
    .water
    0.07
     розп
    0.07
    -report
    0.07
    /by
    0.07
     karar
    0.06
     Derek
    0.06
     railways
    0.06
    idunt
    0.06
     begging
    0.06
     같다
    0.06
    Act Density 0.064%

    No Known Activations