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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    -0.07
     onFailure
    -0.06
    -0.06
    argv
    -0.06
    ación
    -0.06
    VK
    -0.06
     told
    -0.06
     transf
    -0.06
     journalistic
    -0.06
    POSITIVE LOGITS
    甜
    0.08
     Trial
    0.07
    лия
    0.06
    (constants
    0.06
     Kurdistan
    0.06
     trimming
    0.06
    phins
    0.06
     thể
    0.06
     energetic
    0.06
    平台
    0.06
    Act Density 0.000%

    No Known Activations