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

    Neuronpedia

    INDEX
    Explanations

    the end of code comments or certain characters commonly used in programming, as well as HTML tags.

    oai_token-act-pair · gemini-2.0-flash

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.65
    positivos
    -0.60
     يتيمه
    -0.59
     colorés
    -0.59
    unar
    -0.57
    ramientas
    -0.56
     مرئيه
    -0.56
     Agrega
    -0.55
    BufferException
    -0.55
    glEnd
    -0.55
    POSITIVE LOGITS
    <bos>
    1.43
    scalatest
    0.57
    DebuggerNonUser
    0.50
    ıştı
    0.47
    *)((
    0.47
    IBOutlet
    0.47
     rami
    0.43
     seemed
    0.43
    setPref
    0.42
     GLFW
    0.42
    Act Density 0.941%

    No Known Activations