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

    Neuronpedia

    INDEX
    Explanations

    staple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    振り
    -0.07
    剐
    -0.07
    יס
    -0.07
    (-(
    -0.07
     conjunto
    -0.07
     humanoid
    -0.07
    具
    -0.07
    ối
    -0.07
     fruition
    -0.07
    izioni
    -0.07
    POSITIVE LOGITS
     }))↵
    0.08
     heter
    0.07
    */↵
    0.07
    taking
    0.07
    .Source
    0.06
    พวกเขา
    0.06
    标准
    0.06
    Package
    0.06
    Controls
    0.06
    这家公司
    0.06
    Act Density 0.005%

    No Known Activations