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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     여행
    -0.07
    <System
    -0.07
    unset
    -0.07
     reachable
    -0.07
    ủi
    -0.06
    _AA
    -0.06
    coration
    -0.06
     nových
    -0.06
     万
    -0.06
    adapter
    -0.06
    POSITIVE LOGITS
    Austin
    0.07
     bere
    0.06
     Austin
    0.06
     xd
    0.06
     jsx
    0.06
    妹
    0.06
     Další
    0.06
     neue
    0.06
    (counter
    0.06
    ACLE
    0.06
    Act Density 0.040%

    No Known Activations