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

    Neuronpedia

    INDEX
    Explanations

    science research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    archivo
    -0.07
     Spend
    -0.06
     Ευ
    -0.06
    itrust
    -0.06
    idon
    -0.06
    uffer
    -0.06
    灭
    -0.06
     Hartford
    -0.06
     weekday
    -0.06
     plural
    -0.06
    POSITIVE LOGITS
     hlavy
    0.06
    ordan
    0.06
    hope
    0.06
    .xyz
    0.06
    や
    0.06
    Anchor
    0.06
     ×
    0.06
    会社
    0.06
     jmé
    0.06
     Vib
    0.06
    Act Density 0.016%

    No Known Activations