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

    Neuronpedia

    INDEX
    Explanations

    personality types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     payable
    -0.08
     scour
    -0.08
     roundup
    -0.08
     이용
    -0.08
    .create
    -0.08
    INGLE
    -0.08
     unlaw
    -0.08
    手续费
    -0.08
     NGO
    -0.08
     issuer
    -0.08
    POSITIVE LOGITS
     narciss
    0.11
     cognit
    0.11
     cognition
    0.11
     stereotyp
    0.10
     Cognitive
    0.10
     cognitive
    0.10
     Cogn
    0.09
     preference
    0.09
     Preference
    0.09
     psychologists
    0.09
    Act Density 0.013%

    No Known Activations