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

    Neuronpedia

    INDEX
    Explanations

    completeness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )'),↵
    -0.09
     cyl
    -0.07
    zek
    -0.07
    	pstmt
    -0.07
    delivery
    -0.07
    ℃
    -0.07
    🚚
    -0.07
     Applicants
    -0.07
    .getM
    -0.07
    腼
    -0.07
    POSITIVE LOGITS
     reef
    0.07
    BB
    0.07
     Kernel
    0.07
     UF
    0.07
     buổi
    0.07
    ール
    0.07
     בתור
    0.07
    كب
    0.06
     also
    0.06
    .Body
    0.06
    Act Density 0.016%

    No Known Activations