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

    Neuronpedia

    INDEX
    Explanations

    80

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raleigh
    -0.07
     米
    -0.07
    .team
    -0.06
     Ann
    -0.06
     humor
    -0.06
     Emin
    -0.06
     února
    -0.06
     now
    -0.06
     stavu
    -0.06
    Oops
    -0.06
    POSITIVE LOGITS
     superintendent
    0.07
    _sender
    0.07
    чого
    0.06
    territ
    0.06
    Пр
    0.06
     Peripheral
    0.06
     Superintendent
    0.06
    セット
    0.06
     SUBSTITUTE
    0.06
    Decoder
    0.06
    Act Density 0.000%

    No Known Activations