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

    Neuronpedia

    INDEX
    Explanations

    quotes and common phrases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     který
    -0.07
     counter
    -0.07
     vững
    -0.06
    acles
    -0.06
     '@
    -0.06
     descended
    -0.06
    ề
    -0.06
     Dump
    -0.06
     princess
    -0.06
     Tank
    -0.06
    POSITIVE LOGITS
     （
    0.07
    SECTION
    0.06
     yAxis
    0.06
    _registry
    0.06
    омен
    0.06
    ("<?
    0.06
    _reply
    0.06
    �
    0.06
     souha
    0.06
    تب
    0.06
    Act Density 0.004%

    No Known Activations