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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sl
    -0.06
    播
    -0.06
    woo
    -0.06
     hvad
    -0.06
     "#
    -0.06
     Kenn
    -0.06
    _advanced
    -0.06
     nă
    -0.06
     vyjád
    -0.06
     peque
    -0.06
    POSITIVE LOGITS
     procur
    0.07
     harmful
    0.07
    Cursor
    0.07
    ดย
    0.07
    utenant
    0.07
     Zach
    0.07
     scent
    0.07
    .disable
    0.07
     vit
    0.06
     aggregation
    0.06
    Act Density 0.001%

    No Known Activations