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

    Neuronpedia

    INDEX
    Explanations

    direction, state, or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    シル
    0.44
    ண
    0.43
    agem
    0.41
    ែង
    0.41
    classify
    0.41
    ynamics
    0.40
     Nolan
    0.40
     neutralization
    0.40
    اپ
    0.39
    Supp
    0.39
    POSITIVE LOGITS
     पा
    0.49
     pach
    0.49
     hör
    0.49
     கல்லறை
    0.46
    的标准
    0.46
     和
    0.46
    性和
    0.45
    ksh
    0.45
    (%
    0.44
    的对象
    0.44
    Act Density 0.000%

    No Known Activations