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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blink
    -0.07
    abwe
    -0.06
     βρί
    -0.06
    Capabilities
    -0.06
    "While
    -0.06
    ]);
↵
    -0.06
     hiển
    -0.06
    ดาห
    -0.06
    -disabled
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     come
    0.07
    /block
    0.06
    .Open
    0.06
     specify
    0.06
    薩
    0.06
    lač
    0.06
    active
    0.06
     exceeds
    0.06
    noon
    0.06
    /auth
    0.06
    Act Density 0.039%

    No Known Activations