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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bg
    -0.07
    Questions
    -0.07
     Short
    -0.06
     sum
    -0.06
    LOOK
    -0.06
    LOOP
    -0.06
    また
    -0.06
    _TCP
    -0.06
     thighs
    -0.06
    Chess
    -0.06
    POSITIVE LOGITS
    _batch
    0.07
     inhibit
    0.07
    rimon
    0.06
    clazz
    0.06
    567
    0.06
     delivery
    0.06
    اسر
    0.06
     فرزند
    0.06
     dispro
    0.06
    -frequency
    0.06
    Act Density 0.017%

    No Known Activations