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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     with
    -0.07
    .readline
    -0.07
    .ai
    -0.07
    iris
    -0.07
    ퟬ
    -0.07
     présent
    -0.07
    \Input
    -0.06
    .DESC
    -0.06
    olie
    -0.06
     SOS
    -0.06
    POSITIVE LOGITS
     onBackPressed
    0.07
    kn
    0.07
     justified
    0.07
    Iron
    0.07
    �
    0.07
    经销商
    0.07
     grinding
    0.06
    <Renderer
    0.06
    ставлен
    0.06
     onPressed
    0.06
    Act Density 0.005%

    No Known Activations