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

    Neuronpedia

    INDEX
    Explanations

    Bad prognosis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     placer
    -0.08
    men
    -0.08
     infra
    -0.07
     dram
    -0.07
     Maint
    -0.07
    خدمة
    -0.06
    וק
    -0.06
     examined
    -0.06
    Warn
    -0.06
     fora
    -0.06
    POSITIVE LOGITS
     adjacency
    0.07
    _CUDA
    0.07
    �
    0.07
     정말
    0.07
     toned
    0.06
    教室
    0.06
    缢
    0.06
    .partial
    0.06
    _AD
    0.06
    :NSLocalizedString
    0.06
    Act Density 0.033%

    No Known Activations