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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corners
    -0.07
     Oktober
    -0.06
    ụy
    -0.06
    aked
    -0.06
    Exchange
    -0.06
     trends
    -0.06
    urb
    -0.06
     IRequest
    -0.06
     extreme
    -0.06
    atta
    -0.06
    POSITIVE LOGITS
     Venom
    0.07
    animation
    0.07
     wholly
    0.07
    -spec
    0.06
     xmlns
    0.06
     완
    0.06
     splitter
    0.06
    �
    0.06
     NSStringFromClass
    0.06
    _subscribe
    0.06
    Act Density 0.270%

    No Known Activations