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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pendant
    -0.08
     Occasionally
    -0.08
     uncommon
    -0.06
    	signal
    -0.06
     circumference
    -0.06
     Catch
    -0.06
     Kashmir
    -0.06
     Trot
    -0.06
     Ironically
    -0.06
    746
    -0.06
    POSITIVE LOGITS
     д
    0.06
     lesbische
    0.06
    oř
    0.06
    ropriate
    0.06
    lédl
    0.06
    働
    0.06
     Mis
    0.06
    ไหน
    0.06
    ỉ
    0.05
    _HELPER
    0.05
    Act Density 0.018%

    No Known Activations