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

    Neuronpedia

    INDEX
    Explanations

    ival

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dni
    -0.07
     Rosenstein
    -0.07
     büny
    -0.07
    _stdio
    -0.07
    ّ
    -0.07
    _DEFINE
    -0.07
     INTO
    -0.06
    lí
    -0.06
     taxable
    -0.06
    -admin
    -0.06
    POSITIVE LOGITS
     extinction
    0.07
    _hash
    0.06
     category
    0.06
     condom
    0.06
    �
    0.06
    _failure
    0.06
     lược
    0.06
     ук
    0.06
     guide
    0.06
     Shutdown
    0.06
    Act Density 0.006%

    No Known Activations