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

    Neuronpedia

    INDEX
    Explanations

    conn = and conn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ações
    4.47
    e
    4.37
    ej
    4.01
    ei
    3.92
    eer
    3.86
    eo
    3.80
    ੀ
    3.72
    ে
    3.60
    eper
    3.52
    ação
    3.50
    POSITIVE LOGITS
    లో
    4.21
    ن
    3.65
    ate
    3.09
    ()=>{
    3.05
    に
    3.04
    it
    2.92
    getSelectedItem
    2.89
    ך
    2.84
     Archivlink
    2.81
    大气
    2.79
    Act Density 0.012%

    No Known Activations