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

    Neuronpedia

    INDEX
    Explanations

    close carefully

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Glacier
    -0.07
    healthy
    -0.06
    mand
    -0.06
     удов
    -0.06
    iah
    -0.06
     Tablet
    -0.06
     گرم
    -0.06
    óc
    -0.06
     вор
    -0.06
     TL
    -0.06
    POSITIVE LOGITS
     relationships
    0.07
    SingleOrDefault
    0.06
     사람이
    0.06
    ritch
    0.06
     varies
    0.06
     inclus
    0.06
    ังหว
    0.06
    going
    0.06
    ($)
    0.06
     İç
    0.06
    Act Density 0.017%

    No Known Activations