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

    Neuronpedia

    INDEX
    Explanations

    court case citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝐽
    -0.07
    young
    -0.07
    firstname
    -0.07
     hombres
    -0.06
     reelection
    -0.06
     touchscreen
    -0.06
     '?'
    -0.06
    茭
    -0.06
     yyn
    -0.06
    '<
    -0.06
    POSITIVE LOGITS
    ומב
    0.07
     persisted
    0.07
    ,application
    0.07
     doesn
    0.07
    沉淀
    0.07
    也许
    0.07
     metabol
    0.07
     bishops
    0.06
    特别是在
    0.06
    继承
    0.06
    Act Density 0.004%

    No Known Activations