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

    Neuronpedia

    INDEX
    Explanations

    news reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    notif
    -0.07
    Foreground
    -0.07
    нули
    -0.07
    Arn
    -0.07
     yourself
    -0.06
    adapter
    -0.06
     Mission
    -0.06
     Engineering
    -0.06
    Charge
    -0.06
    cart
    -0.06
    POSITIVE LOGITS
     jogo
    0.07
     ağ
    0.06
     próximo
    0.06
     svaz
    0.06
     cambio
    0.06
    ccak
    0.06
     rozší
    0.06
    _-
    0.06
    Ao
    0.06
     чист
    0.06
    Act Density 0.063%

    No Known Activations