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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chapel
    -0.08
    apter
    -0.06
     eş
    -0.06
    _kv
    -0.06
     Ceremony
    -0.06
    енд
    -0.06
    ột
    -0.06
    reste
    -0.06
    anness
    -0.05
     الس
    -0.05
    POSITIVE LOGITS
     přes
    0.07
     chemotherapy
    0.07
    Ports
    0.07
    }`);↵↵
    0.07
    ่ใช
    0.06
    Overflow
    0.06
    /",
    0.06
     allowed
    0.06
     insanların
    0.06
    ");
    0.06
    Act Density 0.001%

    No Known Activations