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

    Neuronpedia

    INDEX
    Explanations

    web pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shallow
    -0.07
     cj
    -0.07
    cpu
    -0.06
    ogeneous
    -0.06
     Taco
    -0.06
    访
    -0.06
     Claw
    -0.06
     gravel
    -0.06
    <Test
    -0.06
     intensive
    -0.06
    POSITIVE LOGITS
    989
    0.07
    983
    0.06
     멀
    0.06
    λί
    0.06
     onslaught
    0.06
    ALT
    0.06
    Angel
    0.06
    .CreateInstance
    0.06
    _seek
    0.06
    precedented
    0.06
    Act Density 0.030%

    No Known Activations