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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ナイス
    0.45
    뤘
    0.45
     повре
    0.44
    rps
    0.43
    imu
    0.43
    ową
    0.43
     רא
    0.43
    ទ្
    0.43
    ovaniyu
    0.42
    厸
    0.41
    POSITIVE LOGITS
    Bor
    0.39
    Celebrate
    0.38
     class
    0.37
     have
    0.37
    Sou
    0.37
     الح
    0.36
    Apple
    0.36
    Solve
    0.36
    Patients
    0.36
     Singapore
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.