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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _GT
    -0.07
     drop
    -0.06
    NE
    -0.06
     Rate
    -0.06
     Raid
    -0.06
    ۵
    -0.06
    video
    -0.06
     fairly
    -0.06
     Collective
    -0.06
     HD
    -0.06
    POSITIVE LOGITS
     которого
    0.07
    epad
    0.06
    @implementation
    0.06
    Division
    0.06
    valor
    0.06
     要
    0.06
    .dimension
    0.06
     drove
    0.06
    .columnHeader
    0.06
    .permission
    0.06
    Act Density 0.034%

    No Known Activations