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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    航海
    -0.07
     Teh
    -0.07
    lığını
    -0.07
    嬰
    -0.07
    voie
    -0.07
     thai
    -0.07
    shade
    -0.07
    衿
    -0.07
    萊
    -0.07
    halb
    -0.07
    POSITIVE LOGITS
     overturned
    0.07
     advances
    0.07
     properly
    0.07
    𝅪
    0.07
     RCA
    0.06
    ⤫
    0.06
    .getNum
    0.06
    噇
    0.06
     libraries
    0.06
    栓
    0.06
    Act Density 0.078%

    No Known Activations