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

    Neuronpedia

    INDEX
    Explanations

    horns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _intersection
    -0.07
     пл
    -0.07
    еня
    -0.07
    ضة
    -0.06
     세계
    -0.06
     утеп
    -0.06
    -Version
    -0.06
     giochi
    -0.06
    plies
    -0.06
     feasible
    -0.06
    POSITIVE LOGITS
     horn
    0.11
     horns
    0.11
     Horn
    0.10
    horn
    0.08
    ORN
    0.07
     Hairst
    0.07
    orn
    0.06
     asia
    0.06
     Maui
    0.06
     histogram
    0.06
    Act Density 0.003%

    No Known Activations