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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attendees
    -0.06
     hc
    -0.06
    -sync
    -0.06
    AAAA
    -0.06
    uu
    -0.06
    杯
    -0.06
     Providence
    -0.06
    _count
    -0.06
     Planning
    -0.06
    .Call
    -0.06
    POSITIVE LOGITS
    (binary
    0.07
     ราค
    0.07
     अगल
    0.07
     соот
    0.07
     README
    0.06
    With
    0.06
    ＝＝
    0.06
     storefront
    0.06
     Skyl
    0.06
    hyp
    0.06
    Act Density 0.000%

    No Known Activations