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

    Neuronpedia

    INDEX
    Explanations

    self-discovery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    هور
    -0.07
    .§
    -0.06
     Section
    -0.06
     flaws
    -0.06
     abilities
    -0.06
    )')↵
    -0.06
    //↵
    -0.06
    38
    -0.06
    へ
    -0.06
    Как
    -0.06
    POSITIVE LOGITS
    rieved
    0.07
     ⟨
    0.06
    VertexUvs
    0.06
     TResult
    0.06
    ertainty
    0.06
    APSHOT
    0.06
     �
    0.06
     uplift
    0.06
     envision
    0.06
     heatmap
    0.06
    Act Density 0.172%

    No Known Activations