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

    Neuronpedia

    INDEX
    Explanations

    istrict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    complexType
    -0.06
     тверд
    -0.06
    sehen
    -0.06
    京
    -0.06
    trimmed
    -0.06
    -bars
    -0.06
    との
    -0.06
     endlessly
    -0.06
    ाय
    -0.06
    .dw
    -0.06
    POSITIVE LOGITS
     Interfaces
    0.07
     collection
    0.07
     Sistem
    0.06
     Ки
    0.06
     invitation
    0.06
     argues
    0.06
     forests
    0.06
     gửi
    0.06
     impact
    0.06
     months
    0.06
    Act Density 0.002%

    No Known Activations