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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    笞
    -0.07
     households
    -0.07
    ße
    -0.07
     networking
    -0.07
     ],↵
    -0.07
    呼
    -0.07
    答疑
    -0.07
     Will
    -0.06
    Survey
    -0.06
    .S
    -0.06
    POSITIVE LOGITS
    ęp
    0.07
    专员
    0.07
     frais
    0.07
    dq
    0.07
     realtime
    0.07
    되면
    0.06
     מצד
    0.06
    >Last
    0.06
     المت
    0.06
    慷
    0.06
    Act Density 0.021%

    No Known Activations