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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ly
    -0.07
    _episode
    -0.07
    /////
    -0.07
    lings
    -0.06
     Seiten
    -0.06
    maintenance
    -0.06
    damn
    -0.06
     prenatal
    -0.06
    artic
    -0.06
     authored
    -0.06
    POSITIVE LOGITS
     �
    0.06
     муж
    0.06
     マ
    0.06
    <select
    0.06
    良
    0.06
     stanov
    0.06
     клі
    0.06
    	Namespace
    0.06
    込み
    0.06
    -selector
    0.06
    Act Density 0.006%

    No Known Activations