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

    Neuronpedia

    INDEX
    Explanations

    zeros

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superficies
    -0.08
     raw
    -0.08
     sp
    -0.07
     remov
    -0.07
     chosen
    -0.07
     hindi
    -0.07
     false
    -0.07
     noise
    -0.07
    ంద్ర
    -0.07
     possibilities
    -0.07
    POSITIVE LOGITS
     responsibly
    0.13
     courteous
    0.11
     respectfully
    0.11
     respeto
    0.10
     politely
    0.10
     सम्मान
    0.10
     respectful
    0.10
     altru
    0.10
     kindly
    0.10
     etiquette
    0.10
    Act Density 0.004%

    No Known Activations