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

    Neuronpedia

    INDEX
    Explanations

    connecting elements and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kit
    0.52
     transformação
    0.47
     वांछ
    0.47
    områ
    0.46
     influencia
    0.46
     importe
    0.46
    的人
    0.46
     cheapest
    0.46
     kunj
    0.46
     kiya
    0.45
    POSITIVE LOGITS
    ០០
    0.46
    ૦
    0.45
    ધાનસભા
    0.44
    s
    0.42
    ༧
    0.41
     항상
    0.41
    ০০
    0.40
    getRedTeam
    0.40
    льм
    0.40
    IFI
    0.40
    Act Density 0.002%

    No Known Activations