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

    Neuronpedia

    INDEX
    Explanations

    ways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вул
    -0.07
    istung
    -0.07
    curso
    -0.06
     Onun
    -0.06
     Eug
    -0.06
     quá
    -0.06
     evaluate
    -0.06
    _refl
    -0.06
    .Host
    -0.06
    อกจาก
    -0.06
    POSITIVE LOGITS
     Dies
    0.07
     Pillow
    0.06
     raison
    0.06
    Ctl
    0.06
     hareket
    0.06
    ifestyle
    0.06
     Russia
    0.06
    ствие
    0.06
    -popup
    0.06
     ICE
    0.06
    Act Density 0.019%

    No Known Activations