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

    Neuronpedia

    INDEX
    Explanations

    Joan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ..
    -0.07
     Protocol
    -0.07
     siege
    -0.07
     Disp
    -0.07
    بدأ
    -0.06
    iyorlar
    -0.06
    ";
↵
    -0.06
    .true
    -0.06
    .Exp
    -0.06
    '):
    -0.06
    POSITIVE LOGITS
     Joan
    0.09
     barely
    0.07
     Coconut
    0.07
     nearly
    0.07
     many
    0.07
    거
    0.07
     finest
    0.07
     Jo
    0.06
     shouldn
    0.06
    unist
    0.06
    Act Density 0.001%

    No Known Activations