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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sock
    -0.07
     ООО
    -0.07
    渫
    -0.07
    efa
    -0.07
     FIFA
    -0.07
     Prostit
    -0.07
     ног
    -0.07
    疹
    -0.07
     narrowly
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     operand
    0.07
     difference
    0.07
    eparator
    0.07
    话
    0.06
    重点关注
    0.06
     ui
    0.06
    '");↵
    0.06
     urlpatterns
    0.06
     사람들이
    0.06
    懷
    0.06
    Act Density 0.001%

    No Known Activations