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

    Neuronpedia

    INDEX
    Explanations

    buy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (edges
    -0.07
     nouns
    -0.07
    -disc
    -0.07
    -Men
    -0.07
     blankets
    -0.07
    (None
    -0.06
     Selbst
    -0.06
    .inv
    -0.06
     ful
    -0.06
    Granted
    -0.06
    POSITIVE LOGITS
    linha
    0.07
     حيث
    0.07
    onic
    0.07
    张家
    0.07
    鲬
    0.06
    떫
    0.06
     hardwood
    0.06
    𖥨
    0.06
    ⚤
    0.06
        ↵↵
    0.06
    Act Density 0.002%

    No Known Activations