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

    Neuronpedia

    INDEX
    Explanations

    interactive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debuted
    -0.06
     Neg
    -0.06
     آینده
    -0.06
     Bott
    -0.06
     halfway
    -0.06
    -vesm
    -0.06
     возмож
    -0.06
    >.
    -0.06
     ध
    -0.06
     exceeded
    -0.06
    POSITIVE LOGITS
    .ReadFile
    0.07
    `↵↵
    0.07
     intellig
    0.06
    .Alignment
    0.06
    /logs
    0.06
    ModifiedDate
    0.06
    _AXIS
    0.06
     приб
    0.06
    visions
    0.06
    -placeholder
    0.06
    Act Density 0.073%

    No Known Activations