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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     and
    -0.76
     And
    -0.56
    and
    -0.56
     There
    -0.54
     When
    -0.54
     Why
    -0.54
     After
    -0.53
    CodeAttribute
    -0.53
     Here
    -0.52
     by
    -0.51
    POSITIVE LOGITS
    +)/
    0.59
    ModelAdmin
    0.58
     ']
    0.57
    DockStyle
    0.57
    >`;
    0.57
    }`).
    0.56
    manni
    0.56
    Endian
    0.56
    …]
    0.56
    ècie
    0.56
    Act Density 0.004%

    No Known Activations