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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ticker
    -0.06
     QQ
    -0.06
     ignition
    -0.06
     країни
    -0.06
    .JScrollPane
    -0.05
    .:.:.:.
    -0.05
     winger
    -0.05
    _ir
    -0.05
    gzip
    -0.05
    :str
    -0.05
    POSITIVE LOGITS
    qn
    0.08
     param
    0.07
     Pattern
    0.07
    прав
    0.07
     src
    0.07
     haven
    0.07
     PURPOSE
    0.07
     Squadron
    0.07
    demo
    0.07
    terrorism
    0.07
    Act Density 0.005%

    No Known Activations