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

    Neuronpedia

    INDEX
    Explanations

    diverse list of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hor
    0.39
     unab
    0.39
    יל
    0.38
    ufthansa
    0.38
    Mild
    0.38
    Turn
    0.37
    gall
    0.37
    堂
    0.37
    Recipient
    0.37
     tenant
    0.37
    POSITIVE LOGITS
    皘
    0.46
     actitud
    0.44
    intage
    0.40
     carácter
    0.38
    起始
    0.38
     پیسې
    0.38
     އަ
    0.38
    стойчи
    0.38
    真實
    0.37
    さが
    0.37
    Act Density 0.000%

    No Known Activations