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

    Neuronpedia

    INDEX
    Explanations

    technical papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kid
    -0.29
    eworld
    -0.28
    欢è¿İæĤ¨
    -0.27
    inkel
    -0.26
     diret
    -0.26
     gim
    -0.26
    ä»İä¸ļ
    -0.25
    entication
    -0.25
    è·¨çķĮ
    -0.25
    PointerException
    -0.24
    POSITIVE LOGITS
     partisan
    0.28
    ↵   ↵
    0.25
     bir
    0.25
    ARK
    0.24
     herself
    0.24
    ark
    0.24
     marked
    0.24
    è¾ĥ好
    0.24
     (`
    0.24
     pd
    0.24
    Act Density 0.007%

    No Known Activations