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

    Neuronpedia

    INDEX
    Explanations

    Hospital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    κα
    -0.07
    وروب
    -0.07
    ίζ
    -0.07
    ฟ
    -0.06
    /java
    -0.06
     конечно
    -0.06
    addWidget
    -0.06
    มอ
    -0.06
    _CONNECTED
    -0.06
    VOKE
    -0.06
    POSITIVE LOGITS
    boss
    0.07
     kort
    0.07
     advisor
    0.07
     detriment
    0.07
    _ref
    0.07
    ↵
    0.07
    ressive
    0.06
    _wait
    0.06
    ':↵↵
    0.06
    Simply
    0.06
    Act Density 0.000%

    No Known Activations