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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KY
    -0.06
    MZ
    -0.06
     dint
    -0.06
    otyping
    -0.06
     hc
    -0.06
    nection
    -0.06
     alkal
    -0.06
     reservation
    -0.06
    .lbl
    -0.05
    Tak
    -0.05
    POSITIVE LOGITS
     말
    0.07
     우
    0.07
    Roman
    0.07
    �
    0.07
    Convention
    0.07
     Gordon
    0.07
     респ
    0.06
    Floor
    0.06
    /root
    0.06
    Lesson
    0.06
    Act Density 0.000%

    No Known Activations