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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MPC
    -0.07
    Env
    -0.07
     Moo
    -0.07
     Tee
    -0.06
    [loc
    -0.06
    基建
    -0.06
    -begin
    -0.06
    ofilm
    -0.06
    )x
    -0.06
    JR
    -0.06
    POSITIVE LOGITS
     Europa
    0.07
    human
    0.07
    代表大会
    0.07
    ไหว
    0.07
    _MAG
    0.07
    Titles
    0.07
    curity
    0.07
    społeczn
    0.07
     entertaining
    0.07
    辘
    0.06
    Act Density 0.018%

    No Known Activations