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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ella
    -0.07
    �
    -0.06
     nhóm
    -0.06
    ũng
    -0.06
    Wy
    -0.06
     zásad
    -0.06
     Asus
    -0.06
     Osmanlı
    -0.06
     cocina
    -0.06
     المع
    -0.06
    POSITIVE LOGITS
    /X
    0.07
    LOCKS
    0.07
    Hz
    0.07
     precaution
    0.06
    leases
    0.06
    处
    0.06
    days
    0.06
    가지
    0.06
    names
    0.06
     muscle
    0.06
    Act Density 0.001%

    No Known Activations