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

    Neuronpedia

    INDEX
    Explanations

    Damage/failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /session
    -0.07
     >>
    -0.06
     Hust
    -0.06
    เซอร
    -0.06
    ати
    -0.06
    основ
    -0.06
    472
    -0.06
    างว
    -0.06
     зі
    -0.06
    唱
    -0.06
    POSITIVE LOGITS
    utive
    0.07
    atican
    0.06
    :'',↵
    0.06
    UMMY
    0.06
     kad
    0.06
    apat
    0.06
    amsung
    0.06
     Calder
    0.06
    /(?
    0.06
     Arbor
    0.06
    Act Density 0.089%

    No Known Activations