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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dana
    -0.07
    -bin
    -0.07
    صور
    -0.06
    <Event
    -0.06
    滿
    -0.06
     انر
    -0.06
     Так
    -0.06
    accumulator
    -0.06
     �
    -0.06
     méth
    -0.06
    POSITIVE LOGITS
     quests
    0.06
    Captain
    0.06
     [<
    0.06
    With
    0.06
    .setTo
    0.06
    Segment
    0.06
     genuine
    0.06
    ровер
    0.06
     Led
    0.06
    Having
    0.06
    Act Density 0.000%

    No Known Activations