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

    Neuronpedia

    INDEX
    Explanations

    relevant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BEGIN
    -0.06
    refund
    -0.06
     Evropy
    -0.06
     hoses
    -0.06
     poop
    -0.06
    (金
    -0.06
    arrings
    -0.06
    人口
    -0.06
     связи
    -0.06
     prototype
    -0.06
    POSITIVE LOGITS
     relevant
    0.08
    _tr
    0.07
     recruiting
    0.06
    Discuss
    0.06
     Sm
    0.06
    _Sh
    0.06
    -num
    0.06
    .d
    0.06
    適
    0.06
    iddleware
    0.06
    Act Density 0.009%

    No Known Activations