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

    Neuronpedia

    INDEX
    Explanations

    cage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OTP
    -0.08
     lanç
    -0.07
    华东
    -0.07
    ONUS
    -0.07
    远方
    -0.07
     hotspot
    -0.07
     artifacts
    -0.07
    domains
    -0.07
     :)
    -0.07
    绨
    -0.06
    POSITIVE LOGITS
    歇
    0.07
    等症状
    0.07
    笼
    0.07
    Cantidad
    0.06
    车企
    0.06
     cage
    0.06
    𫫇
    0.06
     răng
    0.06
    摄像头
    0.06
     closed
    0.06
    Act Density 0.003%

    No Known Activations