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

    Neuronpedia

    INDEX
    Explanations

    Ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harassment
    -0.08
     accidentes
    -0.08
     tecnologías
    -0.07
     réseaux
    -0.07
     uim
    -0.07
     pneus
    -0.07
     uitgebreide
    -0.07
    orset
    -0.07
    éns
    -0.07
    锦
    -0.07
    POSITIVE LOGITS
     başlay
    0.09
     ओर
    0.09
    aptop
    0.08
    開始
    0.08
    ’ordre
    0.08
     البداية
    0.08
     loyalty
    0.08
     شروع
    0.08
     시작
    0.07
     orderly
    0.07
    Act Density 0.028%

    No Known Activations