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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    timestamp
    -0.07
    _stop
    -0.07
     gep
    -0.07
     Dependency
    -0.06
    cassert
    -0.06
     Reach
    -0.06
     Therefore
    -0.06
     Stuff
    -0.06
     brightly
    -0.06
    .pop
    -0.06
    POSITIVE LOGITS
    čník
    0.07
     appear
    0.07
    �
    0.07
     veriler
    0.06
     يت
    0.06
     appeared
    0.06
    _pago
    0.06
     resembling
    0.06
     accomplish
    0.06
    .parameter
    0.06
    Act Density 0.146%

    No Known Activations