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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    찮
    -0.06
     ################################################################
    -0.06
    職
    -0.06
    img
    -0.06
    (nx
    -0.06
     만나
    -0.06
    पत
    -0.06
    ############################################################
    -0.06
     контак
    -0.05
     safari
    -0.05
    POSITIVE LOGITS
     Politico
    0.07
    人物
    0.07
     Επ
    0.07
     wrote
    0.07
     purpos
    0.07
    _pkt
    0.07
     سوی
    0.06
     epub
    0.06
    获
    0.06
     FAILED
    0.06
    Act Density 0.065%

    No Known Activations