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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical language

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    isdiction
    -0.07
    ieg
    -0.06
     +
    -0.06
    Coordinate
    -0.06
     lie
    -0.06
    担当
    -0.06
    !")
↵
    -0.06
    Most
    -0.06
     conna
    -0.06
     wholly
    -0.06
    POSITIVE LOGITS
     }];↵
    0.07
    /items
    0.07
     READY
    0.07
     unveiled
    0.07
    雕塑
    0.07
    refixer
    0.07
    富豪
    0.07
     Soccer
    0.07
    옌
    0.07
    :selected
    0.07
    Act Density 0.515%

    No Known Activations