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

    Neuronpedia

    INDEX
    Explanations

    equation, Schiff, policy, door

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jackie
    0.37
    hus
    0.37
    lowest
    0.36
     week
    0.36
    СР
    0.34
     piggy
    0.34
    erry
    0.34
     cohorts
    0.34
    \}$
    0.34
     Lenn
    0.34
    POSITIVE LOGITS
     FileName
    0.47
     Equation
    0.46
     equation
    0.45
     Allgemeine
    0.45
    檔案
    0.45
    方程
    0.45
     фай
    0.44
     уравнение
    0.43
    Arquivo
    0.43
    Equation
    0.42
    Act Density 0.000%

    No Known Activations