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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StepThrough
    -0.07
    Sit
    -0.07
    "},{"
    -0.06
    Directed
    -0.06
    \F
    -0.06
     říká
    -0.06
    %M
    -0.06
     Tập
    -0.06
    _st
    -0.06
    .square
    -0.06
    POSITIVE LOGITS
     aile
    0.07
     Mirage
    0.07
     ISI
    0.07
     intimately
    0.07
     alone
    0.07
     disappear
    0.07
    ولة
    0.07
     agree
    0.07
     collisions
    0.06
     Parsons
    0.06
    Act Density 0.000%

    No Known Activations