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

    Neuronpedia

    INDEX
    Explanations

    equations with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cube
    0.42
     aus
    0.41
     sini
    0.40
     vom
    0.39
     tumours
    0.37
    Planck
    0.37
    sqrt
    0.36
     ab
    0.36
     anda
    0.36
     tum
    0.36
    POSITIVE LOGITS
     уравнения
    0.48
    经销商
    0.44
    кати
    0.44
     방정식
    0.43
    াওয়া
    0.43
    ेंशन
    0.42
    ósticos
    0.41
     फोर
    0.40
    యోజ
    0.40
     уравнение
    0.40
    Act Density 0.005%

    No Known Activations