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

    Neuronpedia

    INDEX
    Explanations

    Expressing opinions about value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     professor
    -0.07
     board
    -0.07
    urtles
    -0.07
    Aspect
    -0.06
    _Adjust
    -0.06
    ほど
    -0.06
    erna
    -0.06
    flation
    -0.06
     Courts
    -0.06
     piston
    -0.06
    POSITIVE LOGITS
     Southeast
    0.07
    .selection
    0.07
     ];↵
    0.06
     uğra
    0.06
     {↵↵↵
    0.06
    -IS
    0.06
     adverts
    0.06
     Austral
    0.06
     bbw
    0.06
     informat
    0.06
    Act Density 0.064%

    No Known Activations