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

    Neuronpedia

    INDEX
    Explanations

    go

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PEN
    -0.06
    .goal
    -0.06
    pciones
    -0.06
    question
    -0.06
    .blank
    -0.06
    能力
    -0.06
     chờ
    -0.06
    توبر
    -0.06
    pot
    -0.06
     pem
    -0.06
    POSITIVE LOGITS
     overwhelmingly
    0.07
     smoothly
    0.07
     hectic
    0.07
     ordinary
    0.07
    �
    0.07
    logue
    0.06
     Mickey
    0.06
     Cancel
    0.06
    218
    0.06
     disasters
    0.06
    Act Density 0.026%

    No Known Activations