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

    Neuronpedia

    INDEX
    Explanations

    wall type name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prodig
    0.44
    䍜
    0.42
    䐝
    0.42
     Tram
    0.42
    acharya
    0.41
     Reagan
    0.41
     dined
    0.40
    reiro
    0.40
    جور
    0.40
     siglas
    0.40
    POSITIVE LOGITS
    一
    0.70
    gets
    0.51
    0.49
     inclinations
    0.48
     gets
    0.48
    Gets
    0.47
     funerals
    0.47
    Additional
    0.47
    .\"
    0.47
     pallets
    0.46
    Act Density 0.001%

    No Known Activations