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

    Neuronpedia

    INDEX
    Explanations

    disallowing personal information requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typeparam
    -0.10
     pedagog
    -0.09
     rotates
    -0.09
     орт
    -0.09
    phabet
    -0.08
     pedag
    -0.08
     newbie
    -0.08
    rossover
    -0.08
    kušen
    -0.08
     pédagogique
    -0.08
    POSITIVE LOGITS
    查询
    0.11
     requesting
    0.10
     retrieving
    0.09
     개인정보
    0.09
     accessing
    0.09
     조회
    0.09
     retrieval
    0.09
     Privacy
    0.09
     accessed
    0.09
     access
    0.09
    Act Density 0.036%

    No Known Activations