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

    Neuronpedia

    INDEX
    Explanations

    appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reiben
    -0.07
    /Product
    -0.07
     villages
    -0.07
     【
    -0.06
     transcend
    -0.06
    /contentassist
    -0.06
    IE
    -0.06
    EW
    -0.06
     cabinets
    -0.06
     kan
    -0.06
    POSITIVE LOGITS
    CLIENT
    0.07
     authoritarian
    0.07
    })();
    0.06
    luğ
    0.06
    .sep
    0.06
     prevents
    0.06
    Важ
    0.06
    auge
    0.06
     για
    0.06
     Token
    0.06
    Act Density 0.020%

    No Known Activations