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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ud
    -0.07
     Inhal
    -0.07
     Bulk
    -0.07
     שיכול
    -0.07
    Trans
    -0.07
    法治
    -0.07
    Î
    -0.07
    unsupported
    -0.06
     başar
    -0.06
     Tak
    -0.06
    POSITIVE LOGITS
    Plain
    0.07
    更名为
    0.07
     pictured
    0.07
    _price
    0.07
    willReturn
    0.07
    礅
    0.07
    鸮
    0.07
    至尊
    0.07
    北约
    0.06
    _shipping
    0.06
    Act Density 0.040%

    No Known Activations