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

    Neuronpedia

    INDEX
    Explanations

    repri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ization
    -0.65
    UserScript
    -0.65
    ized
    -0.60
    ніципалі
    -0.58
    izations
    -0.57
     onCreate
    -0.57
    SBATCH
    -0.57
    ed
    -0.57
    tinyos
    -0.57
    ised
    -0.55
    POSITIVE LOGITS
     متعلقه
    0.85
     oreilles
    0.58
    TagMode
    0.55
     conçus
    0.54
     feroit
    0.53
     مرئيه
    0.52
    ApiModelProperty
    0.52
     tegas
    0.50
     suivants
    0.50
     stället
    0.50
    Act Density 0.308%

    No Known Activations