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

    Neuronpedia

    INDEX
    Explanations

    space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бы
    -0.07
    ром
    -0.07
     relates
    -0.06
    達
    -0.06
    λλά
    -0.06
    طبيق
    -0.06
    등학교
    -0.06
    APP
    -0.06
     unusually
    -0.06
     обов
    -0.06
    POSITIVE LOGITS
     sidew
    0.07
    Intialized
    0.07
     uncomfortable
    0.07
     slime
    0.06
     avoid
    0.06
     Econom
    0.06
    โด
    0.06
     cardi
    0.06
     harder
    0.06
    ellipsis
    0.06
    Act Density 0.042%

    No Known Activations