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

    Neuronpedia

    INDEX
    Explanations

    names or terms of endearment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inspected
    -0.09
     inspect
    -0.09
     Inspection
    -0.08
    serde
    -0.08
     Brussel
    -0.08
     Landscaping
    -0.08
     inzicht
    -0.08
     elective
    -0.08
     flagged
    -0.08
     muun
    -0.07
    POSITIVE LOGITS
     affectionate
    0.16
     affection
    0.13
    昵称
    0.12
     nostalgic
    0.10
     gọi
    0.09
     cariño
    0.09
     greetings
    0.09
    称
    0.09
     reminis
    0.09
    方式
    0.09
    Act Density 0.020%

    No Known Activations