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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Curriculum
    -0.07
    -anchor
    -0.06
    .Compute
    -0.06
    殂
    -0.06
    兩人
    -0.06
     Vega
    -0.06
     eighth
    -0.06
     ib
    -0.06
     lb
    -0.06
    ili
    -0.06
    POSITIVE LOGITS
    浭
    0.07
    imonial
    0.07
    ystick
    0.07
    .easy
    0.07
    恐怕
    0.06
     sift
    0.06
    assador
    0.06
    것
    0.06
     Javascript
    0.06
    ציוד
    0.06
    Act Density 0.002%

    No Known Activations