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

    Neuronpedia

    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .analysis
    -0.07
     poste
    -0.07
    。あ
    -0.07
     Laos
    -0.07
     unleash
    -0.07
     Launcher
    -0.07
    //================================================================================
    -0.07
    //------------------------------------------------------------------------------------------------
    -0.06
    单
    -0.06
    uvo
    -0.06
    POSITIVE LOGITS
     incident
    0.06
    IDO
    0.06
     міст
    0.06
     deterioration
    0.06
     위해
    0.06
    panels
    0.06
     Scratch
    0.06
    faces
    0.06
    stats
    0.06
     protein
    0.06
    Act Density 0.039%

    No Known Activations