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

    Neuronpedia

    INDEX
    Explanations

    error logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    anglicky
    -0.06
    /Admin
    -0.06
    戶
    -0.06
    □□
    -0.06
    이라고
    -0.06
     bychom
    -0.06
    ysterious
    -0.06
     Tests
    -0.06
    Ale
    -0.06
    POSITIVE LOGITS
     comprehensive
    0.08
     concrete
    0.07
     Concrete
    0.07
     specialty
    0.07
     compliant
    0.07
     пов
    0.06
    Concrete
    0.06
    annah
    0.06
    peat
    0.06
     Georg
    0.06
    Act Density 0.004%

    No Known Activations